Temporal Latent Space Modeling for Community Prediction

Abstract

We propose a temporal latent space model for user community prediction in social networks, whose goal is to predict future emerging user communities based on past history of users' topics of interest. Our model assumes that each user lies within an unobserved latent space, and similar users in the latent space representation are more likely to be members of the same user community. The model allows each user to adjust its location in the latent space as her topics of interest evolve over time. Empirically, we demonstrate that our model, when evaluated on a Twitter dataset, outperforms existing approaches under two application scenarios, namely news recommendation and user prediction on a host of metrics such as mrr, ndcg as well as precision and f-measure.

Catch me if you can: A participant-level rumor detection framework via fine-grained user representation learning

“…Besides, users' stance (Dungs et al, 2018;Li et al, 2019), sentiment (Qin et al, 2021), and intentions are critical in identifying misinformation, which needs careful consideration of why a particular user is involved in retweeting a tweet. Finally, we will extend our model to other downstream tasks, such as rumor spreader prediction (Rath et al, 2021), user interest prediction (Zarrinkalam et al, 2017(Zarrinkalam et al, , 2018, community prediction (Fani et al, 2020), recommendation (Pourali et al, 2019), and information cascades modeling (Chen et al, 2019), etc.…”