Semantic Wide and Deep Learning for Detecting Crisis-Information Categories on Social Media
- Submitting institution
-
The Open University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1587438
- Type
- E - Conference contribution
- DOI
-
10.1007/978-3-319-68288-4_9
- Title of conference / published proceedings
- 16th International Semantic Web Conference
- First page
- 138
- Volume
- -
- Issue
- -
- ISSN
- 0302-9743
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2017
- URL
-
https://www.springer.com/gp/book/9783319682877
- 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
-
2
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents a semantic-deep-learning model to improve crisis management with social media analysis. It has been cited for outperforming alternative models when classifying crisis-related social media content (Kejriwal et al. 2019). The model was used as a benchmark (Sit et al. 2019). This work led to a conference keynote (SocInfo’19), a tutorial at a high impact conference (WWW’2018), and a €2.9M grant (H2020 ID:101003606). Released as add-on to Google Sheets (https://evhart.github.io/crees/), the model was used by 70 users, including CGIAR (Senior Data Manager, CGIAR, details on request); a partnership of international organisations engaged in improving food security during crises.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -