HisRect: Features from Historical Visits and Recent Tweet for Co-Location Judgement

Pengfei Li, Hua Lu, Qian Zheng, Shijian Li, Gang Pan

Research output: Contribution to journalJournal articleResearchpeer-review

1 Citation (Scopus)
226 Downloads (Pure)

Abstract

Enabled by smartphones, social media users are increasingly going mobile. This trend fosters various location based services on social media platforms (e.g., Twitter). Many services like friends notification and community detection benefit from co-location judgement, i.e., to decide whether two Twitter users are co-located in some point-of-interest (POI). This problem is challenging due to the limited information in tweets and the lack of explicit geo-tags in tweets that can be used as labeled data. Our approach to this problem is based on a novel concept of HisRect features extracted from users' historical visits and recent tweets: The former has impacts on where a user visits in general, whereas the latter gives more hints about where a user is currently. In practice, labeled data is scarce. Therefore, we design a semi-supervised learning (SSL) framework that leverages unlabeled data to extract HisRect features. Moreover, we employ an embedding neural network layer to process HisRect features of two users, which decides co-location based on the embedding difference between the two features. Our model is extensively evaluated on two large sets of real Twitter data from more than one million users. The experimental results demonstrate that our HisRect features and SSL framework are highly effective at deciding co-locations. In terms of multiple metrics, our approach clearly outperforms alternative approaches using state-of-the-art techniques.

Original languageEnglish
Article number8798877
JournalI E E E Transactions on Knowledge & Data Engineering
Volume33
Issue number3
Pages (from-to)1005-1018
Number of pages14
ISSN1041-4347
DOIs
Publication statusPublished - 2021

Keywords

  • POI
  • Twitter
  • co-location judgement
  • semi-supervised learning

Fingerprint

Dive into the research topics of 'HisRect: Features from Historical Visits and Recent Tweet for Co-Location Judgement'. Together they form a unique fingerprint.

Cite this