Leap2Trend: A Temporal Word Embedding Approach for Instant Detection of Emerging Scientific Trends
- Submitting institution
-
Birmingham City University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11Z_OP_D2028
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2019.2957440
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 176414
- Volume
- 7
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2019
- 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
-
-
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The proposed Leap2Trend machine learning system proved its ability to instantly identify new scientific trends by learning from text in papers. The novel approach shows its predictability strength when compared to Google Trends. The paper has been recognised by the scholarly data mining community for its significance in Trend Analysis and its reliable experiments in the analysis of semantic change of pairs of words on narrowing a word’s usage ( https://doi.org/10.1007/s11192-020-03610-6 ; 10.1002/widm.1395; 10.1007/s11192-020-03610-6)
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -