Content Driven User Profiling for Comment-Worthy Recommendations of News and Blog Articles Categories and Subject Descriptors. Bansal, T., Das, M., & Bhattacharyya, C. In Proceedings of the 2015 ACM Conference on Recommender Systems, RecSys 2015, pages 195–202, 2015.
doi  abstract   bibtex   
We consider the problem of recommending comment-worthy articles such as news and blog-posts. An article is defined to be comment-worthy for a particular user if that user is interested to leave a comment on it. We note that recommending comment- worthy articles calls for elicitation of commenting-interests of the user from the content of both the articles and the past comments made by users. We thus propose to develop content-driven user profiles to elicit these latent interests of users in commenting and use them to recommend articles for future commenting. The difficulty ofmodeling comment content and the varied nature of users’ commenting interests make the problem technically challenging. The problem of recommending comment-worthy articles is re- solved by leveraging article and comment content through topic modeling and the co-commenting pattern of users through collab- orative filtering, combined within a novel hierarchical Bayesian modeling approach. Our solution, Collaborative Correspondence Topic Models (CCTM), generates user profiles which are lever- aged to provide a personalized ranking of comment-worthy arti- cles for each user. Through these content-driven user profiles, CCTM effectively handle the ubiquitous problem of cold-start without relying on additional meta-data. The inference prob- lem for the model is intractable with no off-the-shelf solution and we develop an efficient Monte Carlo EM algorithm. CCTM is evaluated on three real world data-sets, crawled from two blogs, ArsTechnica (AT) Gadgets (102,087 comments) and AT-Science (71,640 comments), and a news site, DailyMail (33,500 com- ments). We show average improvement of 14% (warm-start) and 18% (cold-start) in AUC, and 80% (warm-start) and 250% (cold-start) in Hit-Rank@5, over state of the art [1, 2].
@inproceedings{Bansal2015,
	title = {Content {Driven} {User} {Profiling} for {Comment}-{Worthy} {Recommendations} of {News} and {Blog} {Articles} {Categories} and {Subject} {Descriptors}},
	isbn = {978-1-4503-3692-5},
	doi = {10.1145/2792838.2800186},
	abstract = {We consider the problem of recommending comment-worthy articles such as news and blog-posts. An article is defined to be comment-worthy for a particular user if that user is interested to leave a comment on it. We note that recommending comment- worthy articles calls for elicitation of commenting-interests of the user from the content of both the articles and the past comments made by users. We thus propose to develop content-driven user profiles to elicit these latent interests of users in commenting and use them to recommend articles for future commenting. The difficulty ofmodeling comment content and the varied nature of users’ commenting interests make the problem technically challenging. The problem of recommending comment-worthy articles is re- solved by leveraging article and comment content through topic modeling and the co-commenting pattern of users through collab- orative filtering, combined within a novel hierarchical Bayesian modeling approach. Our solution, Collaborative Correspondence Topic Models (CCTM), generates user profiles which are lever- aged to provide a personalized ranking of comment-worthy arti- cles for each user. Through these content-driven user profiles, CCTM effectively handle the ubiquitous problem of cold-start without relying on additional meta-data. The inference prob- lem for the model is intractable with no off-the-shelf solution and we develop an efficient Monte Carlo EM algorithm. CCTM is evaluated on three real world data-sets, crawled from two blogs, ArsTechnica (AT) Gadgets (102,087 comments) and AT-Science (71,640 comments), and a news site, DailyMail (33,500 com- ments). We show average improvement of 14\% (warm-start) and 18\% (cold-start) in AUC, and 80\% (warm-start) and 250\% (cold-start) in Hit-Rank@5, over state of the art [1, 2].},
	booktitle = {Proceedings of the 2015 {ACM} {Conference} on {Recommender} {Systems}, {RecSys} 2015},
	author = {Bansal, Trapit and Das, Mrinal and Bhattacharyya, Chiranjib},
	year = {2015},
	keywords = {all or part of, blogs, collaborative filtering, comments, hybrid recommendation systems, news, or, or hard copies of, permission to make digital, this work for personal, topic modeling, user profiling},
	pages = {195--202},
}

Downloads: 0