Topics in Tweets: A User Study of Topic Coherence Metrics for Twitter Data
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-09881
- Type
- E - Conference contribution
- DOI
-
10.1007/978-3-319-30671-1_36
- Title of conference / published proceedings
- ECIR 2016: 38th European Conference on Information Retrieval
- First page
- 492
- Volume
- -
- Issue
- -
- ISSN
- 0302-9743
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- Year of publication
- 2016
- URL
-
http://eprints.gla.ac.uk/116772/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: First topic coherence metrics tailored to Twitter data and aligned with users’ satisfaction. RIGOUR: Uses two datasets obtained from two political election events. Includes a novel and robust evaluation methodology with a corresponding large crowdsourced user study, with 3 state-of-the-art topic modelling approaches and 10 baseline metrics. SIGNIFICANCE: Published at a top IR conference; Best Paper Honorable Mention Award (in top 3 papers out of 201). Topic modelling is a fundamental method used by social scientists to analyse discussions on social media (eg. during elections); Increased coherence in the shown topics allows users to more quickly analyse discussion threads.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -