Amharic  Text-based  Multi-label  Emotion  Classification  on  Social Media Comments using Deep learning

Yeshimebet, Bayu

dc.contributor.author	Yeshimebet, Bayu
dc.date.accessioned	2023-06-19T07:24:52Z
dc.date.available	2023-06-19T07:24:52Z
dc.date.issued	2023-02
dc.identifier.uri	http://ir.bdu.edu.et/handle/123456789/15395
dc.description.abstract	A social media platform is an online platform that people use to develop social networks or relationships with others. Every day, millions of people use different social media to express their thoughts, emotions, and experiences. An emotion is a complex psychological event that involves a mixture of reactions occurring in the human body and brain, usually triggered by a mental content (Almeida et al., 2018). Multi-label text emotion classification is the problem that aims to identify all possible emotions from a given text that best represents the author's mental state. Many researches have been done on text emotion classification in English, Arabic, and Chinese language. However, most of them focus on single-label emotion classification which is unable to identify all present emotions in the given instance. To the best of our knowledge, there is no research done on Amharic text multi-label emotion classification. In addition to this, there is no available dataset to conduct multi-label emotion classification research. These all reason motivates us to do research on multi-label Amharic text emotion classification research. This research is very important for social media authors to know the emotion of their followers or viewers from their comments. To do this research we collected 18000 datasets from different social platforms like YouTube, Facebook, and Twitter. We annotate the dataset by employing psychologist as well as regular users without psychology background. We use word2vec and one hot encoder to prepare the feature vector. We train and test four deep-learning approaches such as LSTM, BILSTM, CNN, and GRU. We perform the experiment by feeding one hot encoding and word2vec features to these four deep learning models and achieve the best accuracy with one hot vector. We achieve test accuracy of 53.1%, 54.5%, 54%, and 39.7% for LSTM, BILSTM, CNN, and GRU respectively. We plan to conduct this research using a large dataset with transformer models (BRT, ROBERTA, and XLNET) and test the performance of these models on Amharic text multi-label emotion classification. Keywords: Amharic text multi-label emotion classification, word2vec, one hot encoder, LSTM, BILSTM, CNN, GRU	en_US
dc.language.iso	en_US	en_US
dc.subject	Computing	en_US
dc.title	Amharic Text-based Multi-label Emotion Classification on Social Media Comments using Deep learning	en_US
dc.type	Thesis	en_US