Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Mathematics and Physics

The aim of this thesis is to develop a robust model with high generalization capability to classify the stance in tweets. In stance detection tasks, the objective is to identify the stance of a person towards a certain topic. To accomplish the thesis objectives, different models were established. Then, two classifiers were trained to evaluate each model. Experimental analyses were conducted on five datasets used as benchmarks for stance detection. Finally, the single models, resulted from the different design alternatives, were combined into three ensemble models. Experimental results show that the proposed ensembles outperform the state-of-the-art models for three out of the five used datasets

Issued also as CD