A Semantic Graph-Based Approach for Radicalisation Detection on Social Media
- Submitting institution
-
The Open University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1458771
- Type
- E - Conference contribution
- DOI
-
10.1007/978-3-319-58068-5_35
- Title of conference / published proceedings
- Lecture Notes in Computer Science
- First page
- 571
- Volume
- 10249
- Issue
- -
- ISSN
- 0302-9743
- Open access status
- Exception within 3 months of publication
- Month of publication
- May
- Year of publication
- 2017
- URL
-
-
- 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
-
4
- Research group(s)
-
-
- Citation count
- 12
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper introduces a novel method to reduce the high false-positives typically introduced by lexicon-based techniques when detecting radicalisation online. Its significance lies in the extensive systematic evaluation performed over 2 million Tweets, which outperformed numerous baselines by a large and statistically significant margin. Paper accepted at ESWC conference (acceptance rate 23%) and cited in several journal papers when pointing to the use of knowledge graphs for better detection of radicalisation (e.g. Kurusuncu et al., 2019, Badawy and Ferrara, 2018, Pirrò 2019). Lead student is now senior data scientist in the HSBC Financial Crime Threat Mitigation unit (details on request).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -