Identification of research hypotheses and new knowledge from scientific literature
- Submitting institution
-
Manchester Metropolitan University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2350
- Type
- D - Journal article
- DOI
-
10.1186/s12911-018-0639-1
- Title of journal
- BMC Medical Informatics and Decision Making
- Article number
- 46
- First page
- -
- Volume
- 18
- Issue
- 1
- ISSN
- 1472-6947
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2018
- URL
-
https://e-space.mmu.ac.uk/620996/
- 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
-
5
- Research group(s)
-
A - Data Science
- Citation count
- 29
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper reports seminal work in biomedical text mining. It presents a novel event-driven meta-knowledge methodology to extract structured information from a text and identifies whether it is related to a research hypothesis the author is making or to new knowledge the author wishes to communicate. Using these techniques, meta-analyses of article collections can be performed. This leads to better categorisation and searching of information in the biomedical literature. Several applications have been reported including bot detection (Mohammad 2019), citation context (Hassan 2018), sentiment analysis (Fouad 2020) leading to an EPSRC fellowship on detection of fake medical news (chrysoula.zerva@manchester.ac.uk).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -