Stance detection in Tweets
Status
Reserved master thesis
Student
- Tianyu Zhu
Formalia
- Targeted audience
-
- AI Bachelor
- Kommedia Bachelor
- Preconditions
-
- Ability to read and understand papers written in English.
- Ability to perform academic writing.
- Good programming skills and ML
- Lectures Information Retrieval oder Information Mining
Task description
In this work the student should analyse stance detection (support, reject, question and commenting) in Twitter, in particular detection of the commenting category with high precision. Stance manual data annotation is labour intensive and costly. Furthermore, most of the tweets annotated for stance end up being in the commenting category. This work should provide a high precision oriented stance classifier to filter out all the tweets that are commenting and give only the remaining tweets for further manual annotation.