This project is hosted by the Security Crime and Intelligence Innovation Institute. We are interested in determining stance and sentiment of collections of posts on social media, and comparing these between different social media platforms. Sentiment refers to the emotional tone of posts; stance refers to the attitude of posts with respect to a particular topic or issue (e.g., positive or negative). There are multiple possible projects here, including: -- Comparing sentiment and/or stance between related topics; -- Comparing sentiment and/or stance for the same topic between different social media platforms; -- Comparing sentiment and/or stance for the same topic for posts expressed in different languages.

The project will initially make use of existing methods for determining sentiment and stance, but there is potential (in advanced variants of the project) to develop new methods.

Students will be supported by members of the Security Crime and Intelligence Innovation Institute team in the sbarc|spark building, and be able to work as peers alongside other students doing variants of this topic.

This project is suitable for students who have studied machine learning and NLP; however, the topic is also open to conversion MSc students who have a keen interest in social media analysis and a willingness to learn NLP/text analytics methods.