TWITOBI: A Recommendation System for Twitter Using Probabilistic Modeling

Author

Kim, Younghoon ; Shim, Kyuseok

Author_Institution

Seoul Nat. Univ., Seoul, South Korea

fYear

2011

fDate

11-14 Dec. 2011

Firstpage

340

Lastpage

349

Abstract

Twitter provides search services to help people find new users to follow by recommending popular users or their friends´ friends. However, these services do not offer the most relevant users to follow for a user. Furthermore, Twitter does not provide yet the search services to find the most interesting tweet messages for a user either. In this paper, we propose TWITOBI, a recommendation system for Twitter using probabilistic modeling for collaborative filtering which can recommend top-K users to follow and top-K tweets to read for a user. Our novel probabilistic model utilizes not only tweet messages but also the relationships between users. We develop an estimation algorithm for learning our model parameters and present its parallelized algorithm using MapReduce to handle large data. Our performance study with real-life data sets confirms the effectiveness and scalability of our algorithms.

Keywords

collaborative filtering; learning (artificial intelligence); probability; recommender systems; social networking (online); MapReduce; TWITOBI; Twitter; collaborative filtering; estimation algorithm; learning; probabilistic modeling; real life data sets; recommendation system; search services; top-k users; Computational modeling; Data models; Equations; Mathematical model; Probabilistic logic; Probability distribution; Twitter; MapReduce; Twitter; collaborative filtering; probabilistic model; recommendation system;

fLanguage

English

Publisher

ieee

Conference_Titel

Data Mining (ICDM), 2011 IEEE 11th International Conference on

Conference_Location

Vancouver,BC

ISSN

1550-4786

Print_ISBN

978-1-4577-2075-8

Type

conf

DOI

10.1109/ICDM.2011.150

Filename

6137238