@inproceedings{jha-etal-2022-curaj,
    title = "{CURAJ}{\_}{IIITDWD}@{LT}-{EDI}-{ACL} 2022: Hope Speech Detection in {E}nglish {Y}ou{T}ube Comments using Deep Learning Techniques",
    author = "Jha, Vanshita  and
      Mishra, Ankit  and
      Saumya, Sunil",
    editor = "Chakravarthi, Bharathi Raja  and
      Bharathi, B  and
      McCrae, John P  and
      Zarrouk, Manel  and
      Bali, Kalika  and
      Buitelaar, Paul",
    booktitle = "Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.ltedi-1.25/",
    doi = "10.18653/v1/2022.ltedi-1.25",
    pages = "190--195",
    abstract = "Hope Speech are positive terms that help to promote or criticise a point of view without hurting the user`s or community`s feelings. Non-Hope Speech, on the other side, includes expressions that are harsh, ridiculing, or demotivating. The goal of this article is to find the hope speech comments in a YouTube dataset. The datasets were created as part of the {\textquotedblleft}LT-EDI-ACL 2022: Hope Speech Detection for Equality, Diversity, and Inclusion{\textquotedblright} shared task. The shared task dataset was proposed in Malayalam, Tamil, English, Spanish, and Kannada languages. In this paper, we worked at English-language YouTube comments. We employed several deep learning based models such as DNN (dense or fully connected neural network), CNN (Convolutional Neural Network), Bi-LSTM (Bidirectional Long Short Term Memory Network), and GRU(Gated Recurrent Unit) to identify the hopeful comments. We also used Stacked LSTM-CNN and Stacked LSTM-LSTM network to train the model. The best macro average F1-score 0.67 for development dataset was obtained using the DNN model. The macro average F1-score of 0.67 was achieved for the classification done on the test data as well."
}