Modeling Temporal Dynamics of User Interests in Online Social Networks

Jiang, Bo; Sha, Ying

doi:10.1016/j.procs.2015.05.275

Cited by 15 publications

(12 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, user interests should be adapted to their recent interests for news or URL recommendations, however, user interests with respect to research may not. Jiang and Sha (2015) also pointed out that users have two types of interests; (1) stable interests (which they call primary interests in Jiang and Sha 2015), and (2) secondary interests. The stable interests of a user are original preferences inherent to that user, such as programmers who like efficient algorithms or lawyers who like debate, etc.…”

Section: Summary and Discussionmentioning

confidence: 99%

“…, Kapanipathi et al (2014), Kang and Lee (2016), Piao and Breslin (2016b,d), Orlandi et al (2012), Weng et al (2010), Michelson and Macskassy (2010), Siehndel and Kawase (2012), Zarrinkalam and Kahani (2015); Zarrinkalam et al (2016), Jiang and Sha (2015), Narducci et al (2013), Xu et al (2011), Nishioka and Scherp (2016); Nishioka et al (2015), Peñas et al (2013), Sang et al (2015), (2016) Acknowledgements This publication has emanated from research conducted with the financial support of Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289 (Insight Centre for Data Analytics). Thanks for the anonymous reviewers and the editor for their constructive feedback to improve this work.…”

Section: Examplesmentioning

confidence: 99%

“…The top two news categories to each tweet based on the cosine similarity between their vectors, and these news categories of a user's tweets are then aggregated to construct the final user interest profiles. Jiang and Sha (2015) leveraged external knowledge sources such as DBpedia, Freebase (Bollacker et al 2008), and Yago (Suchanek et al 2007) for constructing a topic hierarchy tree, which is a hierarchical knowledge base consists of over 1,000 topics distributed in 5 levels. However, the details for obtaining the topic hierarchy tree were not discussed in their study.…”

Section: Profile Enhancementmentioning

confidence: 99%

“…User interests in OSNs can change over time, and many studies have been conducted in order to investigate the temporal dynamics of user interests in OSNs. For example, Jiang and Sha (2015) showed that the similarity of current user interest profiles with the profiles at the beginning of the observation period of their dataset is the lowest while the similarity of current profiles with the ones built in the last month is the highest. Similarly, Abel et al (2011b) showed that a user interest profile built in an earlier week differs more from the current profile compared to one built recently.…”

Section: Temporal Dynamics Of User Interestsmentioning

confidence: 99%

See 3 more Smart Citations

Inferring user interests in microblogging social networks: a survey

Piao

Breslin

2018

User Model User-Adap Inter

View full text Add to dashboard Cite

With the growing popularity of microblogging services such as Twitter in recent years, an increasing number of users are using these services in their daily lives. The huge volume of information generated by users raises new opportunities in various applications and areas. Inferring user interests plays a significant role in providing personalized recommendations on microblogging services, and also on third-party applications providing social logins via these services, especially in cold-start situations. In this survey, we review user modeling strategies with respect to inferring user interests from previous studies. To this end, we focus on four dimensions of inferring user interest profiles: (1) data collection, (2) representation of user interest profiles, (3) construction and enhancement of user interest profiles, and (4) the evaluation of the constructed profiles. Through this survey, we aim to provide an overview of state-of-the-art user modeling strategies for inferring user interest profiles on microblogging social networks with respect to the four dimensions. For each dimension, we review and summarize previous studies based on specified criteria. Finally, we discuss some challenges and opportunities for future work in this research domain.

show abstract

Section: Summary and Discussionmentioning

confidence: 99%

Section: Examplesmentioning

confidence: 99%

Section: Profile Enhancementmentioning

confidence: 99%

Section: Temporal Dynamics Of User Interestsmentioning

confidence: 99%

See 2 more Smart Citations

Inferring user interests in microblogging social networks: a survey

Piao

Breslin

2018

User Model User-Adap Inter

View full text Add to dashboard Cite

show abstract

“…As already intimated, while this study provided valuable information regarding people's interests, it failed to yield any spatial or temporal analysis for deeper, more nuanced understanding. However, a second tier of research does provide either temporal [29][30][31] or spatial analysis [32][33][34] regarding topics of interest. In another approach, the researchers performed both spatial and temporal analysis of their data sets [35][36][37][38], albeit separately (i.e., performing temporal topic analysis, then investigating spatial distributions).…”

Section: Introductionmentioning

confidence: 99%

Applying GIS and Text Mining Methods to Twitter Data to Explore the Spatiotemporal Patterns of Topics of Interest in Kuwait

Almatar

Alazmi

et al. 2020

IJGI

View full text Add to dashboard Cite

Researchers have developed various approaches for exploring the spatial information, temporal patterns, and Twitter content in topics of interest in order to generate a better understanding of human behavior; however, few investigations have integrated these three dimensions simultaneously. This study analyzes the content of tweets in order to conduct a spatiotemporal exploration of the main topics of interest in Kuwait in order to provide a deeper understanding of the topics people think about, when they think about them, and where they tweet about them. To this end, we collect, process, and analyze tweets from nearly 120 areas in Kuwait over a 10-month period. The study’s results indicate that religion, emotions, education, and public policy are the most popular topics of interest in Kuwait. Regarding the spatiotemporal analysis, people post more tweets regarding religion on Fridays, a holy day for Muslims in Kuwait. Moreover, people are more likely to tweet about policy and education on weekdays rather than weekends. In contrast, people tweet about emotional expressions more often on weekends. From the spatial perspectives, spatial clustering in topics occurs across the days of the week. The findings are applicable to further topic analysis and similar research in other countries.

show abstract