Evaluating Link-based Recommendations for Wikipedia. Schwarzer, M., Schubotz, M., Meuschke, N., Breitinger, C., Markl, V., & Gipp, B. In Proceedings of the 16th Annual International ACM/IEEE Joint Conference on Digital Libraries (JCDL), pages 191–200, Newark, New Jersey, USA, June, 2016. ACM. Venue Rating: CORE A*Paper Code/data doi abstract bibtex 1 download Literature recommender systems support users in filtering the vast and increasing number of documents in digital libraries and on the Web. For academic literature, research has proven the ability of citation-based document similarity measures, such as Co-Citation (CoCit), or Co-Citation Proximity Analysis (CPA) to improve recommendation quality. In this paper, we report on the first large-scale investigation of the performance of the CPA approach in generating literature recommendations for Wikipedia, which is fundamentally different from the academic literature domain. We analyze links instead of citations to generate article recommendations. We evaluate CPA, CoCit, and the Apache Lucene MoreLikeThis (MLT) function, which represents a traditional text-based similarity measure. We use two datasets of 779,716 and 2.57 million Wikipedia articles, the Big Data processing framework Apache Flink, and a ten-node computing cluster. To enable our large-scale evaluation, we derive two quasi-gold standards from the links in Wikipedia's "See also" sections and a comprehensive Wikipedia clickstream dataset. Our results show that the citation-based measures CPA and CoCit have complementary strengths compared to the text-based MLT measure. While MLT performs well in identifying narrowly similar articles that share similar words and structure, the citation- based measures are better able to identify topically related information, such as information on the city of a certain university or other technical universities in the region. The CPA approach, which consistently outperformed CoCit, is better suited for identifying a broader spectrum of related articles, as well as popular articles that typically exhibit a higher quality. Additional benefits of the CPA approach are its lower runtime requirements and its language-independence that allows for a cross-language retrieval of articles. We present a manual analysis of exemplary articles to demonstrate and discuss our findings. The raw data and source code of our study, together with a manual on how to use them, are openly available at: https://github.com/wikimedia/citolytics
@inproceedings{SchwarzerSMB16,
address = {Newark, New Jersey, USA},
title = {Evaluating {Link}-based {Recommendations} for {Wikipedia}},
isbn = {978-1-4503-4229-2},
url = {paper=https://www.gipp.com/wp-content/papercite-data/pdf/schwarzer2016.pdf code/data=https://github.com/wikimedia/citolytics},
doi = {10.1145/2910896.2910908},
abstract = {Literature recommender systems support users in filtering the vast and increasing number of documents in digital libraries and on the Web. For academic literature, research has proven the ability of citation-based document similarity measures, such as Co-Citation (CoCit), or Co-Citation Proximity Analysis (CPA) to improve recommendation quality. In this paper, we report on the first large-scale investigation of the performance of the CPA approach in generating literature recommendations for Wikipedia, which is fundamentally different from the academic literature domain. We analyze links instead of citations to generate article recommendations. We evaluate CPA, CoCit, and the Apache Lucene MoreLikeThis (MLT) function, which represents a traditional text-based similarity measure. We use two datasets of 779,716 and 2.57 million Wikipedia articles, the Big Data processing framework Apache Flink, and a ten-node computing cluster. To enable our large-scale evaluation, we derive two quasi-gold standards from the links in Wikipedia's "See also" sections and a comprehensive Wikipedia clickstream dataset.
Our results show that the citation-based measures CPA and CoCit have complementary strengths compared to the text-based MLT measure. While MLT performs well in identifying narrowly similar articles that share similar words and structure, the citation- based measures are better able to identify topically related information, such as information on the city of a certain university or other technical universities in the region. The CPA approach, which consistently outperformed CoCit, is better suited for identifying a broader spectrum of related articles, as well as popular articles that typically exhibit a higher quality. Additional benefits of the CPA approach are its lower runtime requirements and its language-independence that allows for a cross-language retrieval of articles. We present a manual analysis of exemplary articles to demonstrate and discuss our findings. The raw data and source code of our study, together with a manual on how to use them, are openly available at: https://github.com/wikimedia/citolytics},
booktitle = {Proceedings of the 16th {Annual} {International} {ACM}/{IEEE} {Joint} {Conference} on {Digital} {Libraries} ({JCDL})},
publisher = {ACM},
author = {Schwarzer, Malte and Schubotz, Moritz and Meuschke, Norman and Breitinger, Corinna and Markl, Volker and Gipp, Bela},
month = jun,
year = {2016},
note = {Venue Rating: CORE A*},
keywords = {Literature Recommendation},
pages = {191--200},
}
Downloads: 1
{"_id":"G5Kn9ipB9zL4fooxJ","bibbaseid":"schwarzer-schubotz-meuschke-breitinger-markl-gipp-evaluatinglinkbasedrecommendationsforwikipedia-2016","authorIDs":["3aamy24wTzcQoTPGY","7Crs4B84W7BbduMmq","97o4RCsEFAoSxEQqt","9dzP7gNRTLKvc9aPR","GYqCNzAZv2xc9nhmD","KLLNwF6yrTvRfDhAP","LKQ5pS2Y8Pc7FTkr7","TuCkHmKovwKzF3y8Z","ZDet9tokdva7KFSEH","ZJvJiH6kd887XEnz3","gBWY7RvNrDhhspCGi","nLJ4c698vfAyWRWTr","pCb6WupcebiMmhw8Y","qNrPNpAwKg5fp598G","s7Z2R2uTWDHRHN2bE","tFwG3DWb6fYeXs3sL","yiM4TojQ7StGdi2iD"],"author_short":["Schwarzer, M.","Schubotz, M.","Meuschke, N.","Breitinger, C.","Markl, V.","Gipp, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Newark, New Jersey, USA","title":"Evaluating Link-based Recommendations for Wikipedia","isbn":"978-1-4503-4229-2","doi":"10.1145/2910896.2910908","abstract":"Literature recommender systems support users in filtering the vast and increasing number of documents in digital libraries and on the Web. For academic literature, research has proven the ability of citation-based document similarity measures, such as Co-Citation (CoCit), or Co-Citation Proximity Analysis (CPA) to improve recommendation quality. In this paper, we report on the first large-scale investigation of the performance of the CPA approach in generating literature recommendations for Wikipedia, which is fundamentally different from the academic literature domain. We analyze links instead of citations to generate article recommendations. We evaluate CPA, CoCit, and the Apache Lucene MoreLikeThis (MLT) function, which represents a traditional text-based similarity measure. We use two datasets of 779,716 and 2.57 million Wikipedia articles, the Big Data processing framework Apache Flink, and a ten-node computing cluster. To enable our large-scale evaluation, we derive two quasi-gold standards from the links in Wikipedia's \"See also\" sections and a comprehensive Wikipedia clickstream dataset. Our results show that the citation-based measures CPA and CoCit have complementary strengths compared to the text-based MLT measure. While MLT performs well in identifying narrowly similar articles that share similar words and structure, the citation- based measures are better able to identify topically related information, such as information on the city of a certain university or other technical universities in the region. The CPA approach, which consistently outperformed CoCit, is better suited for identifying a broader spectrum of related articles, as well as popular articles that typically exhibit a higher quality. Additional benefits of the CPA approach are its lower runtime requirements and its language-independence that allows for a cross-language retrieval of articles. We present a manual analysis of exemplary articles to demonstrate and discuss our findings. The raw data and source code of our study, together with a manual on how to use them, are openly available at: https://github.com/wikimedia/citolytics","booktitle":"Proceedings of the 16th Annual International ACM/IEEE Joint Conference on Digital Libraries (JCDL)","publisher":"ACM","author":[{"propositions":[],"lastnames":["Schwarzer"],"firstnames":["Malte"],"suffixes":[]},{"propositions":[],"lastnames":["Schubotz"],"firstnames":["Moritz"],"suffixes":[]},{"propositions":[],"lastnames":["Meuschke"],"firstnames":["Norman"],"suffixes":[]},{"propositions":[],"lastnames":["Breitinger"],"firstnames":["Corinna"],"suffixes":[]},{"propositions":[],"lastnames":["Markl"],"firstnames":["Volker"],"suffixes":[]},{"propositions":[],"lastnames":["Gipp"],"firstnames":["Bela"],"suffixes":[]}],"month":"June","year":"2016","note":"Venue Rating: CORE A*","keywords":"Literature Recommendation","pages":"191–200","bibtex":"@inproceedings{SchwarzerSMB16,\n\taddress = {Newark, New Jersey, USA},\n\ttitle = {Evaluating {Link}-based {Recommendations} for {Wikipedia}},\n\tisbn = {978-1-4503-4229-2},\n\turl = {paper=https://www.gipp.com/wp-content/papercite-data/pdf/schwarzer2016.pdf code/data=https://github.com/wikimedia/citolytics},\n\tdoi = {10.1145/2910896.2910908},\n\tabstract = {Literature recommender systems support users in filtering the vast and increasing number of documents in digital libraries and on the Web. For academic literature, research has proven the ability of citation-based document similarity measures, such as Co-Citation (CoCit), or Co-Citation Proximity Analysis (CPA) to improve recommendation quality. In this paper, we report on the first large-scale investigation of the performance of the CPA approach in generating literature recommendations for Wikipedia, which is fundamentally different from the academic literature domain. We analyze links instead of citations to generate article recommendations. We evaluate CPA, CoCit, and the Apache Lucene MoreLikeThis (MLT) function, which represents a traditional text-based similarity measure. We use two datasets of 779,716 and 2.57 million Wikipedia articles, the Big Data processing framework Apache Flink, and a ten-node computing cluster. To enable our large-scale evaluation, we derive two quasi-gold standards from the links in Wikipedia's \"See also\" sections and a comprehensive Wikipedia clickstream dataset.\n\nOur results show that the citation-based measures CPA and CoCit have complementary strengths compared to the text-based MLT measure. While MLT performs well in identifying narrowly similar articles that share similar words and structure, the citation- based measures are better able to identify topically related information, such as information on the city of a certain university or other technical universities in the region. The CPA approach, which consistently outperformed CoCit, is better suited for identifying a broader spectrum of related articles, as well as popular articles that typically exhibit a higher quality. Additional benefits of the CPA approach are its lower runtime requirements and its language-independence that allows for a cross-language retrieval of articles. We present a manual analysis of exemplary articles to demonstrate and discuss our findings. The raw data and source code of our study, together with a manual on how to use them, are openly available at: https://github.com/wikimedia/citolytics},\n\tbooktitle = {Proceedings of the 16th {Annual} {International} {ACM}/{IEEE} {Joint} {Conference} on {Digital} {Libraries} ({JCDL})},\n\tpublisher = {ACM},\n\tauthor = {Schwarzer, Malte and Schubotz, Moritz and Meuschke, Norman and Breitinger, Corinna and Markl, Volker and Gipp, Bela},\n\tmonth = jun,\n\tyear = {2016},\n\tnote = {Venue Rating: CORE A*},\n\tkeywords = {Literature Recommendation},\n\tpages = {191--200},\n}\n\n","author_short":["Schwarzer, M.","Schubotz, M.","Meuschke, N.","Breitinger, C.","Markl, V.","Gipp, B."],"urlpaper":"https://www.gipp.com/wp-content/papercite-data/pdf/schwarzer2016.pdf","urlcode/data":"https://github.com/wikimedia/citolytics","key":"SchwarzerSMB16","id":"SchwarzerSMB16","bibbaseid":"schwarzer-schubotz-meuschke-breitinger-markl-gipp-evaluatinglinkbasedrecommendationsforwikipedia-2016","role":"author","urls":{"Paper":"https://www.gipp.com/wp-content/papercite-data/pdf/schwarzer2016.pdf","Code/data":"https://github.com/wikimedia/citolytics"},"keyword":["Literature Recommendation"],"metadata":{"authorlinks":{"meuschke, n":"https://bibbase.org/show?bib=https%3A%2F%2Fapi.zotero.org%2Fgroups%2F2532143%2Fitems%3Fkey%3DDOjJ33bOgISaFjBIBr7jCV5S%26format%3Dbibtex%26limit%3D100"}},"downloads":1},"bibtype":"inproceedings","biburl":"https://api.zotero.org/groups/2532143/items?key=DOjJ33bOgISaFjBIBr7jCV5S&format=bibtex&limit=100","creationDate":"2020-04-15T13:02:33.681Z","downloads":1,"keywords":["literature recommendation"],"search_terms":["evaluating","link","based","recommendations","wikipedia","schwarzer","schubotz","meuschke","breitinger","markl","gipp"],"title":"Evaluating Link-based Recommendations for Wikipedia","year":2016,"dataSources":["aEHCfX6B2taJt8dfa","9qTaLWxMN5hLpMP8m","xteq4cdC6ATE2G6Fg","JNgeyAG2vQ8k88oYh","FPjHiAkAja6XvmScK","QGwcHf7xnb5mCCQi7","RTGAqwGfLTSqYQMsS","Y7kZGjoN5Erk3Lo2J","yM7MefT3mRkY9m7i4","jnWJCpbQCoWvxj9kz","F32umBkhFrpeJbp7A","BWzEyLkMvdMGpHpr6","hBAe6Z5DsNbrQtje2","e3AdWzdxYmb85Fn5D","MtqPmSRuq4X8FJqNT","YCwvFifyPbazBYMQD","6oZMeYhGKA2Mp8xhF","gYMS6DBXsNosXKcRC","bQwdfx3o8Q3vnsqfH","SzFkcrpurPzNHEyqX","6KJgnNtYZiwwFkcGq","dHLtmS5G7GmooD755"]}