ABSTRACT
Social streams allow users to receive updates from their network by syndicating social media activity. These streams have become a popular way to share and consume information both on the web and in the enterprise. With so much activity going on, filtering and personalizing the stream for individual users is a key challenge. In this work, we study the recommendation of enterprise social stream items through a user survey with 510 participants, conducted within a globally distributed organization. In the survey, participants rated their level of interest and surprise for different items from the stream and could also indicate whether they were already familiar with the item. Thus, our evaluation goes beyond the common accuracy measure and examines aspects of serendipity and novelty. We also inspect how various features of the recommended item, its author, and reader, influence its ratings. Our results shed light on the key factors that make a stream item valuable to its reader within the enterprise.
- Adamopoulos, P. & Tuzhilin, A. 2011. On unexpectedness in recommender systems: or how to expect the unexpected. RecSys '11 Workshop on Novelty and Diversity in RS, 11--18.Google Scholar
- Agarwal, D. et al. 2014. Activity ranking in LinkedIn feed. Proc. KDD '14, 1603--1612. Google ScholarDigital Library
- Amitay, E., Carmel, D., Har'El, N., Ofek-Koifman, S., Soffer, A., Yogev, S., & Golbandi, N. 2009. Social search and discovery using a unified approach. Proc. HT '09, 199--208. Google ScholarDigital Library
- Berkovsky, S., Freyne, J., & Smith, G. 2012. Personalized network updates: increasing social interactions and contributions in social networks. Proc. UMAP '12, 1--13. Google ScholarDigital Library
- Bernstein, M.S., Suh, B., Hong, L., Chen, J., Kairam, S., & Chi, E.H. 2010. Eddi: interactive topic-based browsing of social status streams. Proc. UIST '10, 303--312. Google ScholarDigital Library
- Carmel, D., Uziel, E., Guy, I., Mass, Y., & Roitman, H. 2012. Folksonomy-based term extraction for word cloud generation. ACM TIST, 3(4), 60. Google ScholarDigital Library
- Celma, Ò. & Herrera, P. 2008. A new approach to evaluating novel recommendations. Proc. RecSys '08, 179--186. Google ScholarDigital Library
- Chen, K., Chen, T., Zheng, G., Jin, O., Yao, E., & Yu, Y. 2012. Collaborative personalized tweet recommendation. Proc. SIGIR '12, 661--670. Google ScholarDigital Library
- Cui, P., Wang, F., Liu, S., Ou, M., Yang, S., & Sun, L. 2011. Who should share what?: item-level social influence prediction for users and posts ranking. Proc. SIGIR '11, 185--194. Google ScholarDigital Library
- Daly, E.M., Muller, M.J., Gou, L., & Millen, D.R. 2011. Social lens: personalization around user defined collections for filtering enterprise message streams. Proc. ICWSM '11.Google Scholar
- Desrosiers, C. & Karypis, G. 2011. A comprehensive survey of neighborhood-based recommendation methods. Recommender systems handbook, 107--144.Google Scholar
- DiMicco, J., Millen, D.R., Geyer, W., Dugan, C., Brownholtz, B., & Muller, M. 2008. Motivations for social networking at work. Proc. CSCW '08, 711--720. Google ScholarDigital Library
- Esparza, S.G., O'Mahony, M.P., & Smyth, B. 2013. Catstream: categorising tweets for user profiling and stream filtering. Proc. IUI '13, 25--36. Google ScholarDigital Library
- Facebook for Business -- A Window into News Feed: https://www.facebook.com/business/news/News-Feed-FYI-A-Window-Into-News-FeedGoogle Scholar
- Facebook for Business -- Showing More High Quality Content: https://www.facebook.com/business/news/News-Feed-FYI-Showing-More-High-Quality-ContentGoogle Scholar
- Farrell, S., Lau, T., Nusser, S., Wilcox, E., & Muller, M. 2007. Socially augmenting employee profiles with people-tagging. Proc. UIST '07, 91--100. Google ScholarDigital Library
- Feng, W. & Wang, J. 2013. Retweet or not?: personalized tweet re-ranking. Proc. WSDM '13, 577--586. Google ScholarDigital Library
- Freyne, J., Berkovsky, S., Daly, E.M., & Geyer, W. 2010. Social networking feeds: recommending items of interest. Proc. RecSys '10, 277--280. Google ScholarDigital Library
- Ge, M., Delgado-Battenfeld, C., & Jannach, D. 2010. Beyond accuracy: evaluating recommender systems by coverage and serendipity. Proc. RecSys '10, 257--260. Google ScholarDigital Library
- Guy, I., Ronen, I., & Raviv, A. 2011. Personalized activity streams: sifting through the river of news. Proc. RecSys '11, 181--188. Google ScholarDigital Library
- Guy, I., Steier, T., Barnea, M., Ronen, I., & Daniel, T. 2012. Swimming against the Streamz: search and analytics over the enterprise activity stream. Proc. CIKM '12, 1587--1591. Google ScholarDigital Library
- Guy, I., Steier, T., Barnea, M., Ronen, I., & Daniel, T. 2013. Finger on the pulse: the value of the activity stream in the enterprise. Proc. Interact '13, 411--428.Google ScholarCross Ref
- Guy, I., Ur, S., Ronen, I., Weber, S., & Oral, T. Best faces forward: a large-scale people search in the enterprise. Proc. CHI '12, 1775--1784. Google ScholarDigital Library
- Herlocker, J.L., Konstan, J.A., Terveen, L.G., & Riedl, J.T. 2004. Evaluating collaborative filtering recommender systems. ACM TOIS, 22(1), 5--53. Google ScholarDigital Library
- Hong, L., Bekkerman, R., Adler, J., & Davison, B. D. 2012. Learning to rank social update streams. Proc. SIGIR '12, 651--660. Google ScholarDigital Library
- Iaquinta, L., De Gemmis, M., Lops, P., Semeraro, G., Filannino, M., & Molino, P. 2008. Introducing serendipity in a content-based recommender system. Proc. HIS '08, 168--173. Google ScholarDigital Library
- IBM Connections -- Enterprise Social Software: http://www.ibm.com/software/products/connGoogle Scholar
- Lunze, T., Katz, P., Röhrborn, D., & Schill, A. 2013. Stream-based recommendation for enterprise social media streams. Proc. BIS '13, 175--186.Google ScholarCross Ref
- McCandless, M., Hatcher, E., & Gospodneti, O. 2010. Lucene in action, 2nd edition. Manning Publications Co. Google ScholarDigital Library
- McNee, S.M., Riedl, J., & Konstan, J.A. 2006. Being accurate is not enough: how accuracy metrics have hurt recommender systems. Proc. CHI EA '06, 1097--1101. Google ScholarDigital Library
- McPherson, M., Smith-Lovin, L., & Cook, J.M. 2001. Birds of a feather: Homophily in social networks. Annual review of sociology, 415--444.Google Scholar
- Murakami, T., Mori, K., & Orihara, R. 2007. Metrics for evaluating the serendipity of recommendation lists. Proc. JSAI '07, 40--46. Google ScholarDigital Library
- Onuma, K., Tong, H., & Faloutsos, C. 2009. TANGENT: a novel, 'surprise me', recommendation algorithm. Proc. KDD '09, 657--666. Google ScholarDigital Library
- Paek, T., Gamon, M., Counts, S., Chickering, D. M., & Dhesi, A. 2010. Predicting the importance of newsfeed posts and social network friends. Proc. AAAI '10, 1419--1424.Google ScholarCross Ref
- Ronen, I., Guy, I., Kravi, E., & Barnea, M. Recommending social media items to community owners. Proc. SIGIR '14, 243--252. Google ScholarDigital Library
- Tintarev, N. & Masthoff, J. 2007. A survey of explanations in recommender systems. 3rd WPRSIUI Workshop, Proc. ICED '07, 801--810. Google ScholarDigital Library
- Zhang, Y.C., Séaghdha, D.Ó., Quercia, D., & Jambor, T. 2012. Auralist: introducing serendipity into music recommendation. Proc. WSDM '12, 13--22. Google ScholarDigital Library
- Ziegler, C.N., McNee, S.M., Konstan, J.A., & Lausen, G. 2005. Improving recommendation lists through topic diversification. Proc. WWW '05, 22--32. Google ScholarDigital Library
Index Terms
- Islands in the Stream: A Study of Item Recommendation within an Enterprise Social Stream
Recommendations
On Unexpectedness in Recommender Systems: Or How to Better Expect the Unexpected
Special Sections on Diversity and Discovery in Recommender Systems, Online Advertising and Regular PapersAlthough the broad social and business success of recommender systems has been achieved across several domains, there is still a long way to go in terms of user satisfaction. One of the key dimensions for significant improvement is the concept of ...
Diversity, Serendipity, Novelty, and Coverage: A Survey and Empirical Analysis of Beyond-Accuracy Objectives in Recommender Systems
What makes a good recommendation or good list of recommendations?
Research into recommender systems has traditionally focused on accuracy, in particular how closely the recommender’s predicted ratings are to the users’ true ratings. However, it has been ...
Investigating serendipity in recommender systems based on real user feedback
SAC '18: Proceedings of the 33rd Annual ACM Symposium on Applied ComputingOver the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-...
Comments