Journal of Ambient Intelligence and Smart Environments 5 (2013) 89–104 89 DOI 10.3233/AIS-120191 IOS Press Context-based microblog browsing for mobile users Jonghyun Han a , Xing Xie b,* and Woontack Woo c a School of Information and Communications, Gwangju Institute of Science and Technology, Gwangju, Republic of Korea E-mail: jhan@gist.ac.kr b Microsoft Research Asia, Beijing, China E-mail: xing.xie@microsoft.com c KAIST U-VR Lab., Daejon, Republic of Korea E-mail: wwoo@kaist.ac.kr Abstract. Mobile microblog browsing is inconvenient due to the limitations of mobile devices. Therefore, it is important to effectively retrieve relevant and timely microblog content that caters to the information need of mobile users. In this paper, we first present the findings from a large-scale study on the relationship between microblog content and user context. Then, we show a system that detects local microblog topics, estimates user interests and selects user-preferred topics. The system employs user context to detect microblog topics and post-processes the topics for finding user-preferred content. We exploit time, location, browsing history, social relationship and activity as user context. The effectiveness of our approach is evaluated against several baseline algorithms for investigating the impact of user context on the relevance of retrieved topics. According to our experimental results, the approach enhances the relevance of topics by 24%, compared to the baseline approaches. Thus, we expect that the proposed approach is helpful in advancing mobile information retrieval. Keywords: Mobile context-awareness, microblog analysis, mobile information browsing, microblog topic retrieval, mobile content recommendation 1. Introduction Microblog services have been one of the most popu- lar services on mobile devices. Because of the tremen- dous popularity of them, there has been an explosive increase in the quantities of microblogs. Many users need to browse microblogs on mobile phones for get- ting timely information on the site. Due to the im- provements in the performance of mobile phones, the microblog services are usually combined with intelli- gent services, such as location-based services. How- ever, the limitations of mobile phones – e.g., small dis- play and low computational power – still present diffi- culties in the retrieval and visualization of large quan- tities of microblogs. Thus, it is important to effectively * Corresponding author. retrieve microblog content related to the information needs of mobile users. Recently, many studies have dealt with understand- ing the information needs of mobile users. One re- search field related to understanding mobile infor- mation need is mobile context-aware computing. Al- though mobile applications have limitations compared to desktop applications, it is easier to take advan- tage of a user’s contextual information because mo- bile phones are very personal and have built-in sensors. Contextual information allows websites and applica- tions to provide user-centric content [1,22,24]. Mobile context-awareness has been applied to mobile infor- mation retrieval [4,10,20]. There are also studies re- lated to microblog content retrieval or recommenda- tion [5,15,17]. Those studies mainly focus on extract- ing information from microblogs, instead of under- 1876-1364/13/$27.50 c  2013 – IOS Press and the authors. All rights reserved