Recommender Systems and User Modeling

smiley faces

Recommender systems are ubiquitous in the digital world and largely determine the options that humans get to choose from on web platforms, from online shopping to music streaming. Recommender systems are mostly built upon statistics of past collective user behavior to mimic human preference and decision-making, assuming that users like what similar users liked in the past (so-called collaborative filtering). 

Given their success, such systems indeed seem to capture some of the underlying factors. However, to date, RS do not fully capture the factors leading to human decision-making. We still lack an understanding of important factors such as user intent (i.e., why people listen to music or shop for a particular item) and context-specific decision making (i.e., a user behaving differently in different contexts). 

Our research investigates how such comprehensive user information can effectively be captured in a user model that can be leveraged by recommender systems. Such models need to account for multi-faceted, context-specific user preferences and intents while allowing efficient computation and aggregation. Furthermore, we also advance recommender systems that allow leveraging such comprehensive user models.


Photo by Roman Odintsov at Pexels.

Team

Publications

2015

Bib Link

Martin Pichl, Eva Zangerle and Günther Specht: #nowplaying on #Spotify: Leveraging Spotify Information on Twitter for Artist Recommendations. In Current Trends in Web Engineering, 15th International Conference, ICWE 2015 Workshops (Revised Selected Papers), pages 163-174. Springer, 2015.

2014

Bib Link Download

Martin Pichl, Eva Zangerle and Günther Specht: Combining Spotify and Twitter Data for Generating a Recent and Public Dataset for Music Recommendation. In Proceedings of the 26nd Workshop Grundlagen von Datenbanken (GvDB 2014), Ritten, Italy, vol. 1313, pages 35-40. CEUR-WS.org, Oct. 2014.

Bib Link

Wolfgang Gassler, Eva Zangerle and Günther Specht: Guided Curation of Semistructured Data in Collaboratively-built Knowledge Bases. In Journal on Future Generation Computer Systems, vol. 31, pages 111-119. Elsevier Science Publishers, 2014.

2013

Bib

Eva Zangerle : Exploiting Recommendations in Microblogging Environments. In Scientific Computing@uibk. Innsbruck University Press, 2013.

Bib Link Download

Eva Zangerle, Wolfgang Gassler and Günther Specht: On the Impact of Text Similarity Functions on Hashtag Recommendations in Microblogging Environments. In Social Network Analysis and Mining, vol. 3, no. 4, pages 889-898. Springer Vienna, 2013.

Bib Download

Eva Zangerle: Leveraging Recommender Systems for the Creation and Maintenance of Structure within Collaborative Social Media Platforms. PhD thesis, University of Innsbruck, Department of Computer Science, 2013.

2012

Bib Link Download

Eva Zangerle, Wolfgang Gassler and Günther Specht: Exploiting Twitter's Collective Knowledge for Music Recommendations. In Proceedings of the 2nd Workshop on Making Sense of Microposts (#MSM2012): Big things come in small packages, Lyon, France, 16 April 2012 (in connection with the 21st International Conference on World Wide Web), pages 14-17. 2012

Bib Link

Eva Zangerle and Wolfgang Gassler: Dealing with Structure Heterogeneity in Semantic Collaborative Environments. In Collaboration and the Semantic Web: Social Networks, Knowledge Networks and Knowledge Resources. IGI Publishers, Hershey, Pennsylvania (USA), 2012.

Bib Link Download

Wolfgang Gassler, Eva Zangerle, Martin Bürgler and Günther Specht: SnoopyTagging: Recommending Contextualized Tags to Increase the Quality and Quantity of Meta-Information. In Proceedings of the 21st International Conference on the World Wide Web 2012 (WWW 2012), Lyon, France (Poster), pages 511-512. 2012.

2011

Bib Link Download

Eva Zangerle, Wolfgang Gassler and Günther Specht: Using Tag Recommendations to Homogenize Folksonomies in Microblogging Environments. In Proceedings of the Third International Conference on Social Informatics (SocInfo 2011), Singapore, Singapore, October 6-8, 2011, pages 113-126. Springer, 2011.

Bib Link Download

Wolfgang Gassler, Eva Zangerle and Günther Specht: The Snoopy Concept: Fighting Heterogeneity in Semistructured and Collaborative Information Systems by Using Recommendations. In Proceedings of the 2011 International Conference on Collaboration Technologies and Systems (CTS 2011), pages 61-68. 2011.

Bib Download

Alex Larcher, Eva Zangerle, Wolfgang Gassler and Günther Specht: Key Recommendations for Infoboxes in Wikipedia, 2011, Poster Presentation

2010

Bib Link Download

Wolfgang Gassler, Eva Zangerle, Michael Tschuggnall and Günther Specht: SnoopyDB: Narrowing the Gap between Structured and Unstructured Information using Recommendations. In Proceedings of the 21st ACM Conference on Hypertext and Hypermedia (HT 2010), Toronto, Ontario, Canada, June 13-16, 2010, pages 271-272, 2010.

Bib Link Download

Wolfgang Gassler and Eva Zangerle: Recommendation-Based Evolvement of Dynamic Schemata in Semistructured Information Systems. In Proceedings of the 22nd Workshop Grundlagen von Datenbanken (GvDB 2010), Bad Helmstedt, Germany. CEUR-WS.org, 2010.

Bib Link Download

Eva Zangerle, Wolfgang Gassler and Günther Specht: Recommending Structure in Collaborative Semistructured Information Systems. In Proceedings of the third ACM Conference on Recommender Systems (RecSys 2010), pages 141-145. ACM, 2010.