The objective of this research-in-progress paper is to reveal word semantic change and verify whether the change conforms to the law of differentiation or the law of parallel change. This paper identifies a set of representative words in biomedical literature based on word frequency and word-topic probability distributions. It employs a skip-gram word2vec model to the identified words to measure word-level semantic changes. This paper finds no overwhelming evidence to support either the law of differentiation or the law of parallel change.
|Number of pages||4|
|Publication status||Published - 2017|
|Event||16th International Conference on Scientometrics and Informetrics, ISSI 2017 - Wuhan, China|
Duration: 2017 Oct 16 → 2017 Oct 20
|Other||16th International Conference on Scientometrics and Informetrics, ISSI 2017|
|Period||17/10/16 → 17/10/20|
Bibliographical noteFunding Information:
This project was made possible in part by the Institute of Museum and Library Services (Grant Award Number: RE-07-15-0060-15), for the project titled “Building an entity-based research framework to enhance digital services on knowledge discovery and delivery”.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Applied Mathematics
- Modelling and Simulation
- Statistics and Probability
- Management Science and Operations Research