@inproceedings{hossain-etal-2021-nlp,
    title = "{NLP}-{CUET}@{D}ravidian{L}ang{T}ech-{EACL}2021: Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes",
    author = "Hossain, Eftekhar  and
      Sharif, Omar  and
      Hoque, Mohammed Moshiul",
    editor = "Chakravarthi, Bharathi Raja  and
      Priyadharshini, Ruba  and
      Kumar M, Anand  and
      Krishnamurthy, Parameswari  and
      Sherly, Elizabeth",
    booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
    month = apr,
    year = "2021",
    address = "Kyiv",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2021.dravidianlangtech-1.43/",
    pages = "300--306",
    abstract = "In the past few years, the meme has become a new way of communication on the Internet. As memes are in images forms with embedded text, it can quickly spread hate, offence and violence. Classifying memes are very challenging because of their multimodal nature and region-specific interpretation. A shared task is organized to develop models that can identify trolls from multimodal social media memes. This work presents a computational model that we developed as part of our participation in the task. Training data comes in two forms: an image with embedded Tamil code-mixed text and an associated caption. We investigated the visual and textual features using CNN, VGG16, Inception, m-BERT, XLM-R, XLNet algorithms. Multimodal features are extracted by combining image (CNN, ResNet50, Inception) and text (Bi-LSTM) features via early fusion approach. Results indicate that the textual approach with XLNet achieved the highest weighted f{\_}1-score of 0.58, which enable our model to secure 3rd rank in this task."
}