ABSTRACT
So far it is unclear how different factors of a scientific publication recommender system based on users' tweets have an influence on the recommendation performance. We examine three different factors, namely profiling method, temporal decay, and richness of content. Regarding profiling, we compare CF-IDF that replaces terms in TF-IDF by semantic concepts, HCF-IDF as novel hierarchical variant of CF-IDF, and topic modeling. As temporal decay functions, we apply sliding window and exponential decay. In terms of the richness of content, we compare recommendations using both full-texts and titles of publications and using only titles. Overall, the three factors make twelve recommendation strategies. We have conducted an online experiment with 123 participants and compared the strategies in a within-group design. The best recommendations are achieved by the strategy combining CF-IDF, sliding window, and with full-texts. However, the strategies using the novel HCF-IDF profiling method achieve similar results with just using the titles of the publications. Therefore, HCF-IDF can make recommendations when only short and sparse data is available.
- D. M. Blei and J. D. Lafferty. Dynamic topic models. In ICML. ACM, 2006. Google ScholarDigital Library
- D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichlet allocation. JMLR, 3, 2003. Google ScholarDigital Library
- S. Bostandjiev, J. O'Donovan, and T. Höllerer. Taste- Weights: a visual interactive hybrid recommender system. In RecSys. ACM, 2012. Google ScholarDigital Library
- J. S. Breese, D. Heckerman, and C. Kadie. Empirical analysis of predictive algorithms for collaborative filtering. In UAI. Morgan Kaufmann, 1998. Google ScholarDigital Library
- J. Chen, R. Nairn, L. Nelson, M. Bernstein, and E. Chi. Short and tweet: experiments on recommending content from information streams. In CHI. ACM, 2010. Google ScholarDigital Library
- W. Feng and J. Wang. We can learn your\# hashtags: Connecting tweets to explicit topics. In ICDE. IEEE, 2014.Google Scholar
- F. Goossen, W. IJntema, F. Frasincar, F. Hogenboom, and U. Kaymak. News personalization using the CF- -IDF semantic recommender. In WIMS. ACM, 2011. Google ScholarDigital Library
- T. L. Griffiths and M. Steyvers. Finding scientific topics. NAS, 101, 2004.Google Scholar
- T. J. Hazen. Direct and latent modeling techniques for computing spoken document similarity. In the Spoken Language Technology. IEEE, 2010.Google Scholar
- L. Hong and B. D. Davison. Empirical study of topic modeling in Twitter. In SOMA. ACM, 2010. Google ScholarDigital Library
- D. Jannach, M. Zanker, A. Felfernig, and G. Friedrich. Recommender systems: an introduction. Cambridge University Press, 2010. Google ScholarCross Ref
- P. Kapanipathi, P. Jain, C. Venkataramani, and A. Sheth. User interests identification on Twitter using a hierarchical knowledge base. In ESWC. Springer, 2014.Google ScholarCross Ref
- M. K. Khribi, M. Jemni, and O. Nasraoui. Automatic recommendations for e-learning personalization based on web usage mining techniques and information retrieval. In ICALT. IEEE, 2008. Google ScholarDigital Library
- J. Letierce, A. Passant, J. G. Breslin, and S. Decker. Understanding how twitter is used to spread scientific messages. In WebSci. Web Science Trust, 2010.Google Scholar
- Y. Li, M. Yang, and Z. M. Zhang. Scientific articles recommendation. In CIKM. ACM, 2013. Google ScholarDigital Library
- C. Lu, W. Lam, and Y. Zhang. Twitter user modeling and tweets recommendation based on Wikipedia concept graph. In AAAI Workshops, 2012.Google Scholar
- J. L. Mendoza. A significance test for multisample sphericity. Psychometrika, 45(4), 1980.Google Scholar
- S. E. Middleton, D. C. De Roure, and N. R. Shadbolt. Capturing knowledge of user preferences: ontologies in recommender systems. In K-CAP. ACM, 2001. Google ScholarDigital Library
- C. Nishioka, G. Große-Bölting, and A. Scherp. Influence of time on user profiling and recommending researchers in social media. In i-KNOW. ACM, 2015. Google ScholarDigital Library
- C. Nishioka and A. Scherp. Profiling vs. time vs. content: What does matter for top-k publication recommendation based on twitter profiles? - an extended technical report. http://arxiv.org/abs/1603.07016.Google Scholar
- F. Orlandi, J. Breslin, and A. Passant. Aggregated, interoperable and multi-domain user profiles for the social web. In I-SEMANTICS. ACM, 2012. Google ScholarDigital Library
- S. L. Sangam and S. S. Mogali. Obsolescence of literature in the field of social sciences. PEARL, 7(3), 2013.Google Scholar
- J. P. Shaffer. Modified sequentially rejective multiple test procedures. J. of the ASA, 81(395), 1986.Google Scholar
- W. Shen, J. Wang, P. Luo, and M. Wang. Linking named entities in tweets with knowledge base via user interest modeling. In KDD. ACM, 2013. Google ScholarDigital Library
- S. J. Soltysiak and I. B. Crabtree. Automatic learning of user profiles - towards the personalisation of agent services. BT Tech. J., 16(3), 1998. Google ScholarDigital Library
- K. Sugiyama and M.-Y. Kan. Scholarly paper recommendation via user's recent research interests. In JCDL. ACM, 2010. Google ScholarDigital Library
- K. Sugiyama and M.-Y. Kan. Exploiting potential citation papers in scholarly paper recommendation. In JCDL, pages 153--162. ACM, 2013. Google ScholarDigital Library
- C. Wang and D. M. Blei. Collaborative topic modeling for recommending scientific articles. In KDD. ACM, 2011. Google ScholarDigital Library
- Z. Zhao, Z. Cheng, L. Hong, and E. H. Chi. Improving user topic interest profiles by behavior factorization. In WWW. IW3C2, 2015. Google ScholarDigital Library
Index Terms
- Profiling vs. Time vs. Content: What does Matter for Top-k Publication Recommendation based on Twitter Profiles?
Recommendations
Enriching one-class collaborative filtering with content information from social media
In recent years, recommender systems have become popular to handle the information overload problem of social media websites. The most widely used Collaborative Filtering methods make recommendations by mining users' rating history. However, users' ...
System Level Recommender System for Academic Venue Personalization: Multi vs. Linked Domain
Knowledge Science, Engineering and ManagementAbstractStandard academic venue recommender systems have been emerged aiming to help computer science researchers to find a suitable academic venue, in which they may publish their works. Therefore, using all the available user data provided from various ...
Selecting a small number of products for effective user profiling in collaborative filtering
Collaborative filtering (CF) is one of the most widely used methods for personalized product recommendation at online stores. CF predicts users' preferences on products using past data of users such as purchase records or their ratings on products. The ...
Comments