Fine-grained geolocation of tweets in temporal proximity

• Main Authors: CHONG, Wen Haw, LIM, Ee Peng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Tweet geolocation; temporal proximity; staying behavior; Databases and Information Systems; Social Media
• Online Access: https://ink.library.smu.edu.sg/sis_research/4325; https://ink.library.smu.edu.sg/context/sis_research/article/5328/viewcontent/Fine_grained_Tweets_afv.pdf
• Institution: Singapore Management University

In fine-grained tweet geolocation, tweets are linked to the specific venues (e.g., restaurants, shops) fromwhich they were posted. This explicitly recovers the venue context that is essential for applications such aslocation-based advertising or user profiling. For this geolocation task, we focus on geolocating tweets that arecontained in tweet sequences. In a tweet sequence, tweets are posted from some latent venue(s) by the sameuser and within a short time interval. This scenario arises from two observations: (1) It is quite common thatusers post multiple tweets in a short time and (2) most tweets are not geocoded. To more accurately geolocatea tweet, we propose a model that performs query expansion on the tweet (query) using two novel approaches.The first approachtemporal query expansionconsiders users’ staying behavior around venues. The secondapproachvisitation query expansionleverages on user revisiting the same or similar venues in the past. Wecombine both query expansion approaches via a novel fusion framework and overlay them on a HiddenMarkov Model to account for sequential information. In our comprehensive experiments across multipledatasets and metrics, we show our proposed model to be more robust and accurate than other baselines.