Overview and details of the sessions of this conference. Please select a date or room to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
1State Key Laborotary of Software Engineering, Wuhan Universiy, China; 2School of Infomation Management, Wuhan Universiy, China
Gender prediction has evoked great research interests due to its potential applications like targeted advertisement and personalized search. Most of existing studies rely on the content texts. However, the text information is hard to access. This makes it difficult to extract text features.
In this paper, we propose a novel framework which only involves the users’ ids for gender prediction. The key idea is to represent users in the embedding connection space. We present two strategies to modify the word embedding technique for user embedding. The first is to sequentializing users’ ids to get the order of social context. The second is to embed users into a large-sized sliding window of contexts. We conduct extensive experiments on two real data sets from Sina Weibo. Results show that our method is significantly better than the state-of-the-art graph embedding baselines. Its also accuracy outperforms that of the content based approaches.
User behavior in the Twittersphere: Content analysis of tweets on Charlie Hebdo
Aylin Ilhan, Kaja J. Fietkiewicz
Heinrich Heine University, Germany
The 7th January 2015 is coined by the attacks on Charlie Hebdo in Paris. A lot of people all over the world
showed their solidarity and their emotions by publishing tweets with the hashtag #JeSuisCharlie and
#CharlieHebdo. This study aims at answering, among others, the following questions: What do Twitter
users share and whom do they mention while commenting on terrorist attacks? What are the most
frequently used hashtags? Based on the literature review, the count of retweets can be influenced by
different aspects. This research investigates factors influencing retweeting of tweets on Charlie Hebdo
attacks. Furthermore, it sets a first step into the content analysis of tweets on Charlie Hebdo attacks and
gives a preliminary impression about the user behavior on Twitter.
Rethinking Information Behavior in the Context of Universal Design
Wondwossen Mulualem Beyene, Katriina Byström
Oslo and Akershus University of Applied Sciences, Norway
Universal design represents the idea of designing products and services to be accessible and usable to all, including to persons with disabilities. Its intent in the design of information systems can be understood as tackling user diversity, which relates it to part of studies in human information behavior. Both areas share concerns of users, context, and technology diversity in their respective undertakings. This conceptual paper analyzes the overlaps in the context of each research direction and highlights the challenges to be tackled so that their concerted effort could enhance the design of accessible and usable information systems for all. It also attempts to reexamine the field of information behavior and explore its potential in providing much-needed “human input” to universal design endeavors that have been driven mainly by sets of guidelines and technical specifications.