[ { "key": "774JEUJD", "version": 4, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/774JEUJD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/774JEUJD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "774JEUJD", "version": 4, "itemType": "journalArticle", "title": "", "creators": [], "abstractNote": "", "publicationTitle": "", "publisher": "", "place": "", "date": "", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2020-07-22T12:32:56Z", "dateModified": "2020-07-22T12:32:56Z" } }, { "key": "DJP7ZEI9", "version": 8, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/DJP7ZEI9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/DJP7ZEI9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Finn et al.", "parsedDate": "2012", "numChildren": 1 }, "data": { "key": "DJP7ZEI9", "version": 8, "itemType": "journalArticle", "title": "Making your database available through Wikipedia: the pros and cons", "creators": [ { "creatorType": "author", "firstName": "Robert D", "lastName": "Finn" }, { "creatorType": "author", "firstName": "Paul P", "lastName": "Gardner" }, { "creatorType": "author", "firstName": "Alex", "lastName": "Bateman" } ], "abstractNote": "Wikipedia, the online encyclopedia, is the most famous wiki in use today. It contains over 3.7 million pages of content; with many pages written on scientific subject matters that include peer-reviewed citations, yet are written in an accessible manner and generally reflect the consensus opinion of the community. In this, the 19th Annual Database Issue of Nucleic Acids Research, there are 11 articles that describe the use of a wiki in relation to a biological database. In this commentary, we discuss how biological databases can be integrated with Wikipedia, thereby utilising the pre-existing infrastructure, tools and above all, large community of authors (or Wikipedians). The limitations to the content that can be included in Wikipedia are highlighted, with examples drawn from articles found in this issue and other wiki-based resources, indicating why other wiki solutions are necessary. We discuss the merits of using open wikis, like Wikipedia, versus other models, with particular reference to potential vandalism. Finally, we raise the question about the future role of dedicated database biocurators in context of the thousands of crowdsourced, community annotations that are now being stored in wikis.", "publicationTitle": "Nucleic Acids Research", "publisher": "", "place": "", "date": "Enero 2012", "volume": "40", "issue": "D1", "section": "", "partNumber": "", "partTitle": "", "pages": "D9–D12", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/nar/gkr1195", "citationKey": "", "url": "http://nar.oxfordjournals.org/lookup/doi/10.1093/nar/gkr1195", "accessDate": "", "PMID": "22144683", "PMCID": "", "ISSN": "0305-1048", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Databases" }, { "tag": "Encyclopedias as Topic" }, { "tag": "Factual" }, { "tag": "Internet" }, { "tag": "Systems Integration" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "GW494BJ7", "version": 3, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/GW494BJ7", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/GW494BJ7", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/520089/items/DJP7ZEI9", "type": "application/json" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "GW494BJ7", "version": 3, "parentItem": "DJP7ZEI9", "itemType": "attachment", "linkMode": "imported_file", "title": "Attachment", "accessDate": "", "url": "", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Finn, Gardner, Bateman - 2012 - Making your database available through Wikipedia the pros and cons.pdf", "md5": "e71bbd89beee1ecf2d0060dd235eb364", "mtime": 1461831736000, "tags": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "BC92WMIJ", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/BC92WMIJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/BC92WMIJ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/520089/items/DGHNSUPB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "BC92WMIJ", "version": 2, "parentItem": "DGHNSUPB", "itemType": "note", "note": "

1718941 117-126

", "tags": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "HGAQCERV", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/HGAQCERV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/HGAQCERV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "White and Maessen", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "HGAQCERV", "version": 2, "itemType": "conferencePaper", "title": "ZOT! to wikipedia vandalism: Lab report for PAN at CLEF 2010", "creators": [ { "creatorType": "author", "firstName": "James", "lastName": "White" }, { "creatorType": "author", "firstName": "Rebecca", "lastName": "Maessen" } ], "abstractNote": "This vandalism detector uses features primarily derived from a wordpreserving differencing of the text for each Wikipedia article from before and after the edit, along with a few metadata features and statistics on the before and after text. Features computed from the text difference are then a combination of statistics such as length, markup count, and blanking along with a selected number of TFIDF values for words and bigrams. Our training set was expanded from that supplied for the shared task to include the 5K vandalism edit corpus from West et al. Vandalism edits in the training set that were classified as \"regular\" by a classifier trained on all the data were removed from the training set used for the final classifier. Classification was performed using bagging of the Weka J48graft (C4.5) decision tree [3] which resulted in an evaluation score of 0.84340 AUC. It is unclear whether the expanded vandalism data improved or degraded performance because that changed the ratio of regular to vandalism edits in the training set and we did not make any adjustment for that when training the classifier.", "proceedingsTitle": "CEUR Workshop Proceedings", "conferenceName": "", "publisher": "CEUR-WS", "place": "", "date": "2010", "eventPlace": "", "volume": "1176", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://ceur-ws.org/Vol-1176/CLEF2010wn-PAN-WhiteEt2010.pdf", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "C3PJQAX4", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/C3PJQAX4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/C3PJQAX4", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Harpalani et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "C3PJQAX4", "version": 2, "itemType": "conferencePaper", "title": "Wiki vandalysis - Wikipedia vandalism analysis: Lab report for PAN at CLEF 2010", "creators": [ { "creatorType": "author", "firstName": "Manoj", "lastName": "Harpalani" }, { "creatorType": "author", "firstName": "Thanadit", "lastName": "Phumprao" }, { "creatorType": "author", "firstName": "Megha", "lastName": "Bassi" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Hart" }, { "creatorType": "author", "firstName": "Rob", "lastName": "Johnson" } ], "abstractNote": "Wikipedia describes itself as the \"free encyclopedia that anyone can edit\". Along with the helpful volunteers who contribute by improving the articles, a great number of malicious users abuse the open nature of Wikipedia by vandalizing articles. Deterring and reverting vandalism has become one of the major challenges of Wikipedia as its size grows. Wikipedia editors fight vandalism both manually and with automated bots that use regular expressions and other simple rules to recognize malicious edits[5]. Researchers have also proposed Machine Learning algorithms for vandalism detection[19,15], but these algorithms are still in their infancy and have much room for improvement. This paper presents an approach to fighting vandalism by extracting various features from the edits for machine learning classification. Our classifier uses information about the editor, the sentiment of the edit, the \"quality\" of the edit (i.e. spelling errors), and targeted regular expressions to capture patterns common in blatant vandalism, such as insertion of obscene words or multiple exclamations.We have successfully been able to achieve an area under the ROC curve (AUC) of 0.91 on a training set of 15000 human annotated edits and 0.887 on a random sample of 17472 edits from 317443.", "proceedingsTitle": "CEUR Workshop Proceedings", "conferenceName": "", "publisher": "CEUR-WS", "place": "", "date": "2010", "eventPlace": "", "volume": "1176", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://ceur-ws.org/Vol-1176/CLEF2010wn-PAN-HarpalaniEt2010.pdf", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "38P4UDGW", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/38P4UDGW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/38P4UDGW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Adler et al.", "parsedDate": "2011", "numChildren": 0 }, "data": { "key": "38P4UDGW", "version": 2, "itemType": "bookSection", "title": "Wikipedia Vandalism Detection: Combining Natural Language, Metadata, and Reputation Features", "creators": [ { "creatorType": "author", "firstName": "B Thomas", "lastName": "Adler" }, { "creatorType": "author", "firstName": "Luca", "lastName": "de Alfaro" }, { "creatorType": "author", "firstName": "Santiago M", "lastName": "Mola-Velasco" }, { "creatorType": "author", "firstName": "Paolo", "lastName": "Rosso" }, { "creatorType": "author", "firstName": "Andrew G", "lastName": "West" }, { "creatorType": "editor", "firstName": "A", "lastName": "Gelbukh" } ], "abstractNote": "Wikipedia is an online encyclopedia which anyone can edit. While most edits are constructive, about 7% are acts of vandalism. Such behavior is characterized by modifications made in bad faith; introducing spam and other inappropriate content. In this work, we present the results of an effort to integrate three of the leading approaches to Wikipedia vandalism detection: a spatio-temporal analysis of metadata (STiki), a reputation-based system (WikiTrust), and natural language processing features. The performance of the resulting joint system improves the state-of-the-art from all previous methods and establishes a new baseline for Wikipedia vandalism detection. We examine in detail the contribution of the three approaches, both for the task of discovering fresh vandalism, and for the task of locating vandalism in the complete set of Wikipedia revisions.", "bookTitle": "CICLing'11 Proceedings of the 12th international conference on Computational linguistics and intelligent text processing - Part II", "series": "", "seriesNumber": "", "volume": "6609", "numberOfVolumes": "", "edition": "", "date": "2011", "publisher": "Springer Verlag", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "277–288", "ISBN": "978-3-642-19436-8", "DOI": "", "citationKey": "", "url": "http://link.springer.com/10.1007/978-3-642-19437-5_23", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Wikipedia" }, { "tag": "collaboration" }, { "tag": "machine learning" }, { "tag": "metadata" }, { "tag": "natural-language processing" }, { "tag": "reputation" }, { "tag": "vandalism" }, { "tag": "wiki" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "2ME464P2", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/2ME464P2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/2ME464P2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Mola-Velasco", "parsedDate": "2011", "numChildren": 0 }, "data": { "key": "2ME464P2", "version": 2, "itemType": "conferencePaper", "title": "Wikipedia vandalism detection", "creators": [ { "creatorType": "author", "firstName": "Santiago M.", "lastName": "Mola-Velasco" } ], "abstractNote": "Wikipedia is an online encyclopedia that anyone can access and edit. It has become one of the most important sources of knowledge online and many third party projects rely on it for a wide-range of purposes. The open model of Wikipedia allows pranksters, lobbyists and spammers to attack the integrity of the encyclopedia and this endangers it as a public resource. This is known in the community as vandalism. A plethora of methods have been developed within the Wikipedia and the scientific community to tackle this problem. We have participated in this effort and developed one of the leading approaches. Our research aims to create a fully-working antivandalism system and get it working in the real world. © 2011 ACM.", "proceedingsTitle": "Proceedings of the 20th international conference companion on World wide web - WWW '11", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2011", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "391", "series": "", "seriesNumber": "", "DOI": "10.1145/1963192.1963349", "ISBN": "978-1-4503-0637-9", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?doid=1963192.1963349", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Natural language processing" }, { "tag": "Wikipedia vandalism detection" }, { "tag": "machine learning" }, { "tag": "reputation" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "MB4Z9RCW", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/MB4Z9RCW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/MB4Z9RCW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Cioiu and Rebedea", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "MB4Z9RCW", "version": 2, "itemType": "bookSection", "title": "WikiDetect: Automatic Vandalism Detection for Wikipedia Using Linguistic Features", "creators": [ { "creatorType": "author", "firstName": "Dan", "lastName": "Cioiu" }, { "creatorType": "author", "firstName": "Traian", "lastName": "Rebedea" }, { "creatorType": "editor", "firstName": "Costin", "lastName": "Bǎdicǎ" }, { "creatorType": "editor", "firstName": "Ngoc Thanh", "lastName": "Nguyen" }, { "creatorType": "editor", "firstName": "Marius", "lastName": "Brezovan" } ], "abstractNote": "Vandalism of the content has always been one of the greatest problems for Wikipedia, yet only few completely automatic solutions for solving it have been developed so far. Volunteers still spend large amounts of time correcting vandalized page edits, instead of using this time to improve the quality of the content of articles. The purpose of this paper is to introduce a new vandalism detection system, that only uses natural language processing and machine learning techniques. The system has been evaluated on a corpus of real vandalized data in order to test its performance and justify the design choices. The same expert annotated wikitext, extracted from the encyclopedia's database, is used to evaluate different vandalism detection algorithms. The paper presents a critical analysis of the obtained results, comparing them to existing solutions, and suggests different statistical classification methods that bring several improvements to the task at hand. © Springer-Verlag 2013.", "bookTitle": "Computational Collective Intelligence. Technologies and Applications 5th International Conference, ICCCI 2013, Craiova, Romania, September 11-13, 2013. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lec", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "volume": "8083", "numberOfVolumes": "", "edition": "", "date": "2013", "publisher": "Springer Berlin Heidelberg", "place": "Berlin, Heidelberg", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "316–325", "ISBN": "978-3-642-40494-8", "DOI": "", "citationKey": "", "url": "http://link.springer.com/10.1007/978-3-642-40495-5_32", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Classification" }, { "tag": "Natural language processing" }, { "tag": "Vandalism detection" }, { "tag": "Wikipedia" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "IKNVUZKN", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/IKNVUZKN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/IKNVUZKN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Flekova et al.", "parsedDate": "2014", "numChildren": 0 }, "data": { "key": "IKNVUZKN", "version": 2, "itemType": "conferencePaper", "title": "What makes a good biography?", "creators": [ { "creatorType": "author", "firstName": "Lucie", "lastName": "Flekova" }, { "creatorType": "author", "firstName": "Oliver", "lastName": "Ferschke" }, { "creatorType": "author", "firstName": "Iryna", "lastName": "Gurevych" } ], "abstractNote": "With more than 22 million articles, the largest collaborative knowledge resource never sleeps, experiencing several article edits every second. Over one fifth of these articles describes individual people, the majority of which are still alive. Such articles are, by their nature, prone to corruption and vandalism. Manual quality assurance by experts can barely cope with this massive amount of data. Can it be effectively replaced by feedback from the crowd? Can we provide meaningful support for quality assurance with automated text processing techniques? Which properties of the articles should then play a key role in the machine learning algorithms and why? In this paper, we study the user-perceived quality of Wikipedia articles based on a novel Wikipedia user feedback dataset. In contrast to previous work on quality assessment which mostly relied on judgements of active Wikipedia authors, we analyze ratings of ordinary Wikipedia users along four quality dimensions (complete, well written, trustworthy and objective). We first present an empirical analysis of the novel dataset with over 36 million Wikipedia article ratings. We then select a subset of biographical articles and perform classification experiments to predict their quality ratings along each of the dimensions, exploring multiple linguistic, surface and network properties of the rated articles. Additionally, we study the classification performance and differences for the biographies of living and dead people as well as those for men and women. We demonstrate the effectiveness of our approach by the F1 scores of 0.94, 0.89, 0.73, and 0.73 for the dimensions complete, well written, trustworthy, and objective. Based on the results, we believe that the quality assessment of big textual data can be effectively supported by current text classification and language processing tools. Copyright is held by the International World Wide Web Conference Committee (IW3C2).", "proceedingsTitle": "Proceedings of the 23rd international conference on World wide web - WWW '14", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2014", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "855–866", "series": "WWW '14", "seriesNumber": "", "DOI": "10.1145/2566486.2567972", "ISBN": "978-1-4503-2744-2", "citationKey": "", "url": "http://doi.acm.org/10.1145/2566486.2567972 http://dl.acm.org/citation.cfm?doid=2566486.2567972", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Natural language processing" }, { "tag": "Quality assessment" }, { "tag": "Wikipedia" }, { "tag": "collaborative knowledge resources" }, { "tag": "document classification" }, { "tag": "machine learning" }, { "tag": "neutrality" }, { "tag": "trustworthiness" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "ZQ4GESKC", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/ZQ4GESKC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/ZQ4GESKC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Alfonseca et al.", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "ZQ4GESKC", "version": 2, "itemType": "journalArticle", "title": "WHAD: Wikipedia historical attributes data", "creators": [ { "creatorType": "author", "firstName": "Enrique", "lastName": "Alfonseca" }, { "creatorType": "author", "firstName": "Guillermo", "lastName": "Garrido" }, { "creatorType": "author", "firstName": "Jean-Yves", "lastName": "Delort" }, { "creatorType": "author", "firstName": "Anselmo", "lastName": "Peñas" } ], "abstractNote": "This paper describes the generation of temporally anchored infobox attribute data from the Wikipedia history of revisions. By mining (attribute, value) pairs from the revision history of the English Wikipedia we are able to collect a comprehensive knowledge base that contains data on how attributes change over time. When dealing with the Wikipedia edit history, vandalic and erroneous edits are a concern for data quality. We present a study of vandalism identification in Wikipedia edits that uses only features from the infoboxes, and show that we can obtain, on this dataset, an accuracy comparable to a state-of-the-art vandalism identification method that is based on the whole article. Finally, we discuss different characteristics of the extracted dataset, which we make available for further study.", "publicationTitle": "Language Resources and Evaluation", "publisher": "", "place": "", "date": "Diciembre 2013", "volume": "47", "issue": "4", "section": "", "partNumber": "", "partTitle": "", "pages": "1163–1190", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1007/s10579-013-9232-5", "citationKey": "", "url": "http://link.springer.com/10.1007/s10579-013-9232-5", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1574-020X", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Attributes" }, { "tag": "Infobox" }, { "tag": "Temporal data" }, { "tag": "Wikipedia" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "CFI6Z4KX", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/CFI6Z4KX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/CFI6Z4KX", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Javanmardi et al.", "parsedDate": "2011", "numChildren": 0 }, "data": { "key": "CFI6Z4KX", "version": 2, "itemType": "conferencePaper", "title": "Vandalism detection in Wikipedia: A High-performing, Feature-rich Model and Its Reduction Through Lasso", "creators": [ { "creatorType": "author", "firstName": "Sara", "lastName": "Javanmardi" }, { "creatorType": "author", "firstName": "David W.", "lastName": "McDonald" }, { "creatorType": "author", "firstName": "Cristina V.", "lastName": "Lopes" } ], "abstractNote": "User generated content (UGC) constitutes a significant fraction of the Web. However, some wiiki-based sites, such as Wikipedia, are so popular that they have become a favorite target of spammers and other vandals. In such popular sites, human vigilance is not enough to combat vandalism, and tools that detect possible vandalism and poor-quality contributions become a necessity. The application of machine learning techniques holds promise for developing efficient online algorithms for better tools to assist users in vandalism detection. We describe an efficient and accurate classifier that performs vandalism detection in UGC sites. We show the results of our classifier in the PAN Wikipedia dataset. We explore the effectiveness of a combination of 66 individual features that produce an AUC of 0.9553 on a test dataset - the best result to our Lasso optimizationknowledge. Using Lasso optimization we then reduce our feature - rich model to a much smaller and more efficient model of 28 features that performs almost as well - the drop in AUC being only 0.005. We describe how this approach can be generalized to other user generated content systems and describe several applications of this classifier to help users identify potential vandalism. © 2011 ACM.", "proceedingsTitle": "Proceedings of the 7th International Symposium on Wikis and Open Collaboration - WikiSym '11", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2011", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "82", "series": "", "seriesNumber": "", "DOI": "10.1145/2038558.2038573", "ISBN": "978-1-4503-0909-7", "citationKey": "", "url": "http://pensivepuffin.comwww.pensivepuffin.com/dwmcphd/papers/Javanmardi.et.al-Vandalism-WikiSym11.pdf", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Lasso" }, { "tag": "Vandalism detection" }, { "tag": "Wikipedia" }, { "tag": "random forests" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "JKCJCQ4G", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/JKCJCQ4G", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/JKCJCQ4G", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Roessing", "parsedDate": "2011", "numChildren": 0 }, "data": { "key": "JKCJCQ4G", "version": 2, "itemType": "conferencePaper", "title": "Vandalism and conflict resolution in wikipedia. An empirical analysis on how a large-scale web-based community deals with breaches of the online peace", "creators": [ { "creatorType": "author", "firstName": "Thomas", "lastName": "Roessing" } ], "abstractNote": "The paper discusses the proceedings on the anti-vandalism page of the German language version of the online encyclopedia Wikipedia. Research questions address the structure of vandalism reports, the distribution over timeEstudio of day and the relationship between conflict potential and conflict resolution. A quantitative analysis of 500 vandalism reports reveals that the anti-vandalism page is a good indicator for conflicts within the community and its deficits in dealing with them.", "proceedingsTitle": "Proceedings of the IADIS International Conferences - Web Based Communities and Social Media 2011, Social Media 2011, Internet Applications and Research 2011, Part of the IADIS, MCCSIS 2011", "conferenceName": "", "publisher": "", "place": "", "date": "2011", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "81–86", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "978-972-8939-40-3", "citationKey": "", "url": "https://www.researchgate.net/profile/Thomas_Roessing/publication/260385752_Vandalism_and_conflict_resolution_in_wikipedia._An_empirical_analysis_on_how_a_large-scale_web-based_community_deals_with_breaches_of_the_online_peace/links/5512be1e0cf20bfdad51e57", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Conflict" }, { "tag": "Conflict resolution" }, { "tag": "Web-based community" }, { "tag": "Wikipedia" }, { "tag": "vandalism" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "FTE28N5N", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/FTE28N5N", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/FTE28N5N", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Itakura and Clarke", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "FTE28N5N", "version": 2, "itemType": "conferencePaper", "title": "Using dynamic markov compression to detect vandalism in the wikipedia", "creators": [ { "creatorType": "author", "firstName": "Kelly Y.", "lastName": "Itakura" }, { "creatorType": "author", "firstName": "Charles L. A.", "lastName": "Clarke" } ], "abstractNote": "We apply the Dynamic Markov Compression model to detect spam edits in the Wikipedia. The method appears to outperform previous efforts based on compression models, providing performance comparable to methods based on manually constructed rules.", "proceedingsTitle": "Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval - SIGIR '09", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "822–823", "series": "", "seriesNumber": "", "DOI": "10.1145/1571941.1572146", "ISBN": "978-1-60558-483-6", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?doid=1571941.1572146", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Information retrieval" }, { "tag": "Spam filtering" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "3DH3VXXG", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/3DH3VXXG", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/3DH3VXXG", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Javanmardi et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "3DH3VXXG", "version": 2, "itemType": "conferencePaper", "title": "User contribution and trust in Wikipedia", "creators": [ { "creatorType": "author", "firstName": "Sara", "lastName": "Javanmardi" }, { "creatorType": "author", "firstName": "Yasser", "lastName": "Ganjisaffar" }, { "creatorType": "author", "firstName": "Cristina", "lastName": "Lopes" }, { "creatorType": "author", "firstName": "Pierre", "lastName": "Baldi" } ], "abstractNote": "Wikipedia, one of the top ten most visited websites, is commonly viewed as the largest online reference for encyclopedic knowledge. Because of its open editing model -allowing anyone to enter and edit content- Wikipedia's overall quality has often been questioned as a source of reliable information. Lack of study of the open editing model of Wikipedia and its effectiveness has resulted in a new generation of wikis that restrict contributions to registered users only, using their real names. In this paper, we present an empirical study of user contributions to Wikipedia. We statistically analyze contributions by both anonymous and registered users. The results show that submissions of anonymous and registered users in Wikipedia suggest a power law behavior. About 80% of the revisions are submitted by less than 7% of the users, most of whom are registered users. To further refine the analyzes, we use the Wiki Trust Model (WTM), a user reputation model developed in our previous work to assign a reputation value to each user. As expected, the results show that registered users contribute higher quality content and therefore are assigned higher reputation values. However, a significant number of anonymous users also contribute high-quality content. We provide further evidence that regardless of a user s' attribution, registered or anonymous, high reputation users are the dominant contributors that actively edit Wikipedia articles in order to remove vandalism or poor quality content.", "proceedingsTitle": "Proceedings of the 5th International ICST Conference on Collaborative Computing: Networking, Applications, Worksharing", "conferenceName": "", "publisher": "IEEE", "place": "", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "10.4108/ICST.COLLABORATECOM2009.8376", "ISBN": "978-963-9799-76-9", "citationKey": "", "url": "http://eudl.eu/doi/10.4108/ICST.COLLABORATECOM2009.8376 http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5365214&filter=AND(p_Publication_Number:5353246)", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "CH964R9M", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/CH964R9M", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/CH964R9M", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Ba et al.", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "CH964R9M", "version": 2, "itemType": "conferencePaper", "title": "Uncertain version control in open collaborative editing of tree-structured documents", "creators": [ { "creatorType": "author", "firstName": "M. Lamine", "lastName": "Ba" }, { "creatorType": "author", "firstName": "Talel", "lastName": "Abdessalem" }, { "creatorType": "author", "firstName": "Pierre", "lastName": "Senellart" } ], "abstractNote": "In order to ease content enrichment, exchange, and sharing, web-scale collaborative platforms such as Wikipedia or Google Docs enable unbounded interactions between a large number of contributors, without prior knowledge of their level of expertise and reliability. Version control is then essential for keeping track of the evolution of the shared content and its provenance. In such environments, uncertainty is ubiquitous due to the unreliability of the sources, the incompleteness and imprecision of the contributions, the possibility of malicious editing and vandalism acts, etc. To handle this uncertainty, we use a probabilistic XML model as a basic component of our version control framework. Each version of a shared document is represented by an XML tree and the whole document, together with its different versions, is modeled as a probabilistic XML document. Uncertainty is evaluated using the probabilistic model and the reliability measure associated to each source, each contributor, or each editing event, resulting in an uncertainty measure on each version and each part of the document. We show that standard version control operations can be implemented directly as operations on the probabilistic XML model; efficiency with respect to deterministic version control systems is demonstrated on real-world datasets.", "proceedingsTitle": "Proceedings of the 2013 ACM symposium on Document engineering - DocEng '13", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2013", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "27", "series": "", "seriesNumber": "", "DOI": "10.1145/2494266.2494277", "ISBN": "978-1-4503-1789-4", "citationKey": "", "url": "http://dl.acm.org/citation.cfm?doid=2494266.2494277", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "collaborative work" }, { "tag": "uncertain data" }, { "tag": "version control" }, { "tag": "xml" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "DGHNSUPB", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/DGHNSUPB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/DGHNSUPB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Geiger and Ribes", "parsedDate": "2010", "numChildren": 1 }, "data": { "key": "DGHNSUPB", "version": 2, "itemType": "book", "title": "The work of sustaining order in wikipedia: the banning of a vandal", "creators": [ { "creatorType": "author", "firstName": "R Stuart", "lastName": "Geiger" }, { "creatorType": "author", "firstName": "David", "lastName": "Ribes" } ], "abstractNote": "In this paper, we examine the social roles of software tools in the English-language Wikipedia, specifically focusing on autonomous editing programs and assisted editing tools. This qualitative research builds on recent research in which we quantitatively demonstrate the growing prevalence of such software in recent years. Using trace ethnography, we show how these often-unofficial technologies have fundamentally transformed the nature of editing and administration in Wikipedia. Specifically, we analyze \"vandal fighting\" as an epistemic process of distributed cognition, highlighting the role of non-human actors in enabling a decentralized activity of collective intelligence. In all, this case shows that software programs are used for more than enforcing policies and standards. These tools enable coordinated yet decentralized action, independent of the specific norms currently in force.", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2010", "publisher": "ACM", "place": "Savannah, GA, USA", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "117–126", "ISBN": "", "DOI": "", "citationKey": "", "url": "https://dl.acm.org/citation.cfm?id=1718941", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "DU7TCUFM", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/DU7TCUFM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/DU7TCUFM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "de Laat", "parsedDate": "2015-09", "numChildren": 0 }, "data": { "key": "DU7TCUFM", "version": 2, "itemType": "journalArticle", "title": "The use of software tools and autonomous bots against vandalism: eroding Wikipedia's moral order?", "creators": [ { "creatorType": "author", "firstName": "Paul B.", "lastName": "de Laat" } ], "abstractNote": "English-language Wikipedia is constantly being plagued by vandalistic contributions on a massive scale. In order to fight them its volunteer contributors deploy an array of software tools and autonomous bots. After an analysis of their functioning and the ‘coactivity' in use between humans and bots, this research ‘discloses' the moral issues that emerge from the combined patrolling by humans and bots. Administrators provide the stronger tools only to trusted users, thereby creating a new hierarchical layer. Further, surveillance exhibits several troubling features: questionable profiling practices (concerning anonymous users in particular), the use of the controversial measure of reputation (under consideration), ‘oversurveillance' where quantity trumps quality, and a prospective loss of the required moral skills whenever bots take over from humans. The most troubling aspect, though, is that Wikipedia has become a Janus-faced institution. One face is the basic platform of MediaWiki software, transparent to all. Its other face is the anti-vandalism system, which, in contrast, is opaque to the average user, in particular as a result of the algorithms and neural networks in use. Finally it is argued that this secrecy impedes a much needed discussion to unfold; a discussion that should focus on a ‘rebalancing' of the anti-vandalism system and the development of more ethical information practices towards contributors.", "publicationTitle": "Ethics and Information Technology", "publisher": "", "place": "", "date": "Septiembre 2015", "volume": "17", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "175–188", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1007/s10676-015-9366-9", "citationKey": "", "url": "http://link.springer.com/10.1007/s10676-015-9366-9", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1388-1957", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Bots" }, { "tag": "Disclosive ethics" }, { "tag": "Profiling" }, { "tag": "Surveillance" }, { "tag": "Wikipedia" }, { "tag": "vandalism" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "U3ZV98AE", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/U3ZV98AE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/U3ZV98AE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Segall and Greenstadt", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "U3ZV98AE", "version": 2, "itemType": "conferencePaper", "title": "The illiterate editor: metadata-driven revert detection in Wikipedia", "creators": [ { "creatorType": "author", "firstName": "Jeffrey", "lastName": "Segall" }, { "creatorType": "author", "firstName": "Rachel", "lastName": "Greenstadt" } ], "abstractNote": "As the community depends more heavily on Wikipedia as a source of reliable information, the ability to quickly detect and remove detrimental information becomes increasingly important. The longer incorrect or malicious information lingers in a source perceived as reputable, the more likely that information will be accepted as correct and the greater the loss to source reputation. We present The Illiterate Editor (IllEdit), a content-agnostic, metadata-driven classification approach to Wikipedia revert detection. Our primary contribution is in building a metadata-based feature set for detecting edit quality, which is then fed into a Support Vector Machine for edit classification. By analyzing edit histories, the IllEdit system builds a profile of user behavior, estimates expertise and spheres of knowledge, and determines whether or not a given edit is likely to be eventually reverted. The success of the system in revert detection (0.844 F-measure) as well as its disjoint feature set as compared to existing, content-analyzing vandalism detection systems, shows promise in the synergistic usage of IllEdit for increasing the reliability of community information.", "proceedingsTitle": "Proceedings of the 9th International Symposium on Open Collaboration - WikiSym '13", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2013", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1–8", "series": "", "seriesNumber": "", "DOI": "10.1145/2491055.2491066", "ISBN": "978-1-4503-1852-5", "citationKey": "", "url": "http://dl.acm.org/citation.cfm?doid=2491055.2491066", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "2ITRFXCI", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/2ITRFXCI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/2ITRFXCI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "West et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "2ITRFXCI", "version": 2, "itemType": "conferencePaper", "title": "STiki: An Anti-vandalism Tool for Wikipedia Using Spatio-temporal Analysis of Revision Metadata", "creators": [ { "creatorType": "author", "firstName": "Andrew G.", "lastName": "West" }, { "creatorType": "author", "firstName": "Sampath", "lastName": "Kannan" }, { "creatorType": "author", "firstName": "Insup", "lastName": "Lee" } ], "abstractNote": "STiki is an anti-vandalism tool for Wikipedia. Unlike similar tools, STiki does not rely on natural language processing (NLP) over the article or diff text to locate vandalism. Instead, STiki leverages spatio-temporal properties of revision metadata. The feasibility of utilizing such properties was demonstrated in our prior work, which found they perform comparably to NLP-efforts while being more efficient, robust to evasion, and language independent. STiki is a real-time, on-Wikipedia implementation based on these properties. It consists of, (1) a server-side processing engine that examines revisions, scoring the likelihood each is vandalism, and, (2) a client-side GUI that presents likely vandalism to end-users for definitive classification (and if necessary, reversion on Wikipedia). Our demonstration will provide an introduction to spatio-temporal properties, demonstrate the STiki software, and discuss alternative research uses for the open-source code. © 2010 ACM.", "proceedingsTitle": "Proceedings of the 6th International Symposium on Wikis and Open Collaboration - WikiSym '10", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1", "series": "", "seriesNumber": "", "DOI": "10.1145/1832772.1832814", "ISBN": "978-1-4503-0056-8", "citationKey": "", "url": "http://repository.upenn.edu/cgi/viewcontent.cgi?article=1490&context=cis_papers", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "MQRCQ9KW", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/MQRCQ9KW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/MQRCQ9KW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "West et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "MQRCQ9KW", "version": 2, "itemType": "conferencePaper", "title": "Spatio-temporal analysis of Wikipedia metadata and the STiki anti-vandalism tool", "creators": [ { "creatorType": "author", "firstName": "Andrew G.", "lastName": "West" }, { "creatorType": "author", "firstName": "Sampath", "lastName": "Kannan" }, { "creatorType": "author", "firstName": "Insup", "lastName": "Lee" } ], "abstractNote": "The bulk of Wikipedia anti-vandalism tools require natural language processing over the article or diff text. However, our prior work demonstrated the feasibility of using spatio-temporal properties to locate malicious edits. STiki is a real-time, on-Wikipedia tool leveraging this technique. The associated poster reviews STiki's methodology and performance. We find competing anti-vandalism tools inhibit maximal performance. However, the tool proves particularly adept at mitigating long-term embedded vandalism. Further, its robust and language-independent nature make it well-suited for use in less-patrolled Wiki installations.", "proceedingsTitle": "Proceedings of the 6th International Symposium on Wikis and Open Collaboration - WikiSym '10", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1", "series": "", "seriesNumber": "", "DOI": "10.1145/1832772.1832797", "ISBN": "978-1-4503-0056-8", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?doid=1832772.1832797", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "384DUWRE", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/384DUWRE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/384DUWRE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Kardan et al.", "parsedDate": "2014-09", "numChildren": 0 }, "data": { "key": "384DUWRE", "version": 2, "itemType": "conferencePaper", "title": "SigmoRep: A Robust Reputation Model for Open Collaborative Environments", "creators": [ { "creatorType": "author", "firstName": "Ahmad A.", "lastName": "Kardan" }, { "creatorType": "author", "firstName": "Reza", "lastName": "Salarmehr" }, { "creatorType": "author", "firstName": "Azade", "lastName": "Farshad" } ], "abstractNote": "In recent years, numerous collaborative web applications have been successfully used to create encyclopedias, learning-objects, maps and even artworks. Trust and reputation systems are two important components of all collaborative information repositories such as Wikipedia. The open nature of such repositories encourages users to contribute to the application. However, this also makes vandalism and low quality contribution possible. Reputation systems try to provide some mechanisms to evaluate the quality of contributions and prevent malicious and untrusted users from harming the resources and encourage constructive behaviors. In this paper, we present an innovative reputation system named SigmoRep, which uses article evaluation patterns to calculate the author's reputation values. It uses a function called controlled influence function to prevent oligarchy. In this paper, we also investigate the evaluation of Wikipedia's articles at the fragment level. Our reputation system is resistant to a wide range of related attacks and is more human-understandable than other similar systems.", "proceedingsTitle": "2014 IEEE 13th International Conference on Trust, Security and Privacy in Computing and Communications", "conferenceName": "", "publisher": "IEEE", "place": "", "date": "Septiembre 2014", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "505–510", "series": "", "seriesNumber": "", "DOI": "10.1109/TrustCom.2014.64", "ISBN": "978-1-4799-6513-7", "citationKey": "", "url": "http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7011288", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Open collaboration" }, { "tag": "Reputation system" }, { "tag": "Trust" }, { "tag": "wiki" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "6RAJ758Z", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/6RAJ758Z", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/6RAJ758Z", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Suzuki and Yoshikawa", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "6RAJ758Z", "version": 2, "itemType": "conferencePaper", "title": "QualityRank: Assessing Quality of Wikipedia Articles by Mutually Evaluating Editors and Texts", "creators": [ { "creatorType": "author", "firstName": "Yu", "lastName": "Suzuki" }, { "creatorType": "author", "firstName": "Masatoshi", "lastName": "Yoshikawa" } ], "abstractNote": "In this paper, we propose a method to identify high-quality Wikipedia articles by mutually evaluating editors and texts. A major approach for assessing articles using edit history is a text survival ratio based approach. However, the problem is that many high-quality articles are identified as low quality, because many vandals delete high-quality texts, then the survival ratios of high-quality texts are decreased by vandals. Our approach's strongest point is its resistance to vandalism. Using our method, if we calculate text quality values using editor quality values, vandals do not affect any quality values of the other editors, then the accuracy of text quality values should improve. However, the problem is that editor quality values are calculated by text quality values, and text quality values are calculated by editor quality values. To solve this problem, we mutually calculate editor and text quality values until they converge. Using this method, we can calculate a quality value of a text that takes into consideration that of its editors. From experimental evaluation, we confirmed that the proposed method can improve the accuracy of quality values for articles.", "proceedingsTitle": "Proceedings of the 23rd ACM conference on Hypertext and social media - HT '12", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2012", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "307", "series": "", "seriesNumber": "", "DOI": "10.1145/2309996.2310047", "ISBN": "978-1-4503-1335-3", "citationKey": "", "url": "http://www.cs.uwm.edu/ munson/ht_12/ht/p307.pdf", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Edit history" }, { "tag": "Link analysis" }, { "tag": "Peer review" }, { "tag": "quality" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "3IEUASDA", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/3IEUASDA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/3IEUASDA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Suzuki and Yoshikawa", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "3IEUASDA", "version": 2, "itemType": "conferencePaper", "title": "Mutual evaluation of editors and texts for assessing quality of Wikipedia articles", "creators": [ { "creatorType": "author", "firstName": "Yu", "lastName": "Suzuki" }, { "creatorType": "author", "firstName": "Masatoshi", "lastName": "Yoshikawa" } ], "abstractNote": "In this paper, we propose a method to identify good quality Wikipedia articles by mutually evaluating editors and texts. A major approach for assessing article quality is a text survival ratio based approach. In this approach, when a text survives beyond multiple edits, the text is assessed as good quality. This approach assumes that poor quality texts are deleted by editors with high possibility. However, many vandals delete good quality texts frequently, then the survival ratios of good quality texts are improperly decreased by vandals. As a result, many good quality texts are unfairly assessed as poor quality. In our method, we consider editor quality for calculating text quality, and decrease the impacts on text qualities by the vandals who has low quality. Using this improvement, the accuracy of the text quality should be improved. However, an inherent problem of this idea is that the editor qualities are calculated by the text qualities. To solve this problem, we mutually calculate the editor and text qualities until they converge. We did our experimental evaluation, and we confirmed that the proposed method could accurately assess the text qualities.", "proceedingsTitle": "Proceedings of the Eighth Annual International Symposium on Wikis and Open Collaboration - WikiSym '12", "conferenceName": "", "publisher": "ACM Press", "place": "New York, New York, USA", "date": "2012", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1", "series": "WikiSym '12", "seriesNumber": "", "DOI": "10.1145/2462932.2462956", "ISBN": "978-1-4503-1605-7", "citationKey": "", "url": "http://doi.acm.org/10.1145/2462932.2462956 http://dl.acm.org/citation.cfm?doid=2462932.2462956", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Edit history" }, { "tag": "Link analysis" }, { "tag": "Peer review" }, { "tag": "Wikipedia" }, { "tag": "quality" } ], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } }, { "key": "2WJJR2UA", "version": 2, "library": { "type": "group", "id": 520089, "name": "Wikipedia Vandalism Literature Review", "links": { "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/520089/items/2WJJR2UA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/wikipedia_vandalism_literature_review/items/2WJJR2UA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 184246, "username": "tramullas", "name": "Jesús Tramullas", "links": { "alternate": { "href": "https://www.zotero.org/tramullas", "type": "text/html" } } }, "creatorSummary": "Wöhner et al.", "parsedDate": "2015-06", "numChildren": 0 }, "data": { "key": "2WJJR2UA", "version": 2, "itemType": "journalArticle", "title": "Managed Wikis: A New Approach for Web 2.0", "creators": [ { "creatorType": "author", "firstName": "Thomas", "lastName": "Wöhner" }, { "creatorType": "author", "firstName": "Sebastian", "lastName": "Köhler" }, { "creatorType": "author", "firstName": "Ralf", "lastName": "Peters" } ], "abstractNote": "Wiki projects can be edited by everyday web users directly within the web browser. Consequently, undesirable contributions like vandalism and spam cannot be ruled out. In this paper, Managed Wikis are introduced as a new approach to avoid such undesirable contributions. Editing rights are assigned according to author reputation, the quality of articles and the occurrence of patterns of suspicious edits. In the paper, the concept of Managed Wikis is evaluated by means of a simulation on the basis of Wikipedia data. The analysis proves that undesirable contributions are blocked effectively. In contrast, desirable contributions are rarely affected by the editing rights restriction. The concept of Managed Wikis addresses open as well as corporate wiki projects where undesirable edits cause significant harm. Furthermore, it can be applied to make traditional websites accessible for the web community.", "publicationTitle": "Business & Information Systems Engineering", "publisher": "", "place": "", "date": "Junio 2015", "volume": "57", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "155–166", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1007/s12599-015-0378-0", "citationKey": "", "url": "http://link.springer.com/10.1007/s12599-015-0378-0", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "2363-7005", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-04-28T08:22:15Z", "dateModified": "2016-04-28T08:22:15Z" } } ]