A methodology for the resolution of cashtag collisions on Twitter – A natural language processing & data fusion approach
- Submitting institution
-
Manchester Metropolitan University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2359
- Type
- D - Journal article
- DOI
-
10.1016/j.eswa.2019.03.019
- Title of journal
- Expert Systems with Applications
- Article number
- -
- First page
- 353
- Volume
- 127
- Issue
- -
- ISSN
- 0957-4174
- Open access status
- Compliant
- Month of publication
- March
- Year of publication
- 2019
- URL
-
https://e-space.mmu.ac.uk/622767/
- 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)
-
C - Machine Intelligence
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents an original methodology for resolving the problem of cashtag ‘collisions’ which can confuse investors using social media and online platforms. The research discovered that cashtag collisions are not limited to companies listed on stock exchanges as they were also increasingly being confused with dominant cryptocurrency tickers. The research helps businesses and investors to save time. The research led to the creation of a novel real-world dataset containing a larger cashtag space than any existing work. The paper has influenced other financial researchers and is cited in a new ‘model’ for dealing with radio frequency interference in astronomy.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -