Sentiment Analysis on Twitter and Health Data
Introduction
Sentiment analysis, also called opinion mining, is the field of study that analyzes people’s opinions, sentiments, evaluations, appraisals, attitudes, and emotions towards entities such as products, services, organizations, individuals, issues, events, topics, and their attributes.
Approach
- Automated Topic Extraction (generic Machine Learning model).
- Automated polarity attributions to the ‘effect’ entities in the corpus (Dictionary module)
- An algorithm to access the effect annotations and assign an overall polarity based on context and relationships between them(rule based).
- Experimenting with an UI to analyze results.
Analytical Processing Module
Machine Learning Module
Technology
- Web Interfaces are designed using HTML5
- Analytical graphs are implemented with the use of graphic library like HighCharts
- Communicate with Analysis Web services through a series of Ajax calls
