Book chapter
Discovering Consumer Health Expressions from Consumer-Contributed Content
Social Computing, Behavioral-Cultural Modeling and Prediction, pp 164-174
2013
Abstract
It has long been recognized that health consumers and professionals use different vocabularies to express health related concepts. Consumers often find it difficult to understand medical terminologies. If consumers misinterpret the health information they received and rely on it for decision making, this language gap would cause severe consequences. Many efforts have been taken to build Consumer Health Vocabulary (CHV) to bridge the gap and facilitate health information consuming. Extracting vocabularies used by consumers to express health concepts is a significant as well as challenging subtask in developing CHV. However, few studies have focused on developing methods for extracting consumer health expressions. In this work, we proposed a semi-automatic method that employs Principal Components Analysis (PCA) and Logistic Regression for identifying consumer health expressions from consumer-contributed content in social media. The experiment results showed that the proposed method is effective in identifying consumer health expressions from consumer-contributed content. These identified expressions can help to extend CHV and to enhance the performance of Adverse Drug Reactions (ADRs) signals detection.
Metrics
5 Record Views
19 citations in Scopus
Details
- Title
- Discovering Consumer Health Expressions from Consumer-Contributed Content
- Creators
- Ling Jiang - Drexel UniversityChristopher C. Yang - Drexel UniversityJiexun Li - Drexel UniversityJingjing Li - Urban Health Collaborative (2015-)
- Publication Details
- Social Computing, Behavioral-Cultural Modeling and Prediction, pp 164-174
- Series
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg; Berlin, Heidelberg
- Resource Type
- Book chapter
- Language
- English
- Academic Unit
- Information Science (Informatics); Urban Health Collaborative
- Scopus ID
- 2-s2.0-84874814633
- Other Identifier
- 991019174003904721