Topic-Specific Sentiment Analysis Can Help Identify Political Ideology
This work addresses the problem of political ideology detection for researchers and analysts, but it is incremental as it builds on existing sentiment analysis methods.
The paper tackled the problem of identifying political ideology by proposing a framework that represents ideology as a distribution of sentiment polarities towards topics, achieving comparable performance to other methods on a widely used dataset.
Ideological leanings of an individual can often be gauged by the sentiment one expresses about different issues. We propose a simple framework that represents a political ideology as a distribution of sentiment polarities towards a set of topics. This representation can then be used to detect ideological leanings of documents (speeches, news articles, etc.) based on the sentiments expressed towards different topics. Experiments performed using a widely used dataset show the promise of our proposed approach that achieves comparable performance to other methods despite being much simpler and more interpretable.