@inproceedings{li-etal-2022-multimodal,
    title = "Multimodal Conversation Modelling for Topic Derailment Detection",
    author = "Li, Zhenhao  and
      Rei, Marek  and
      Specia, Lucia",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.findings-emnlp.376/",
    doi = "10.18653/v1/2022.findings-emnlp.376",
    pages = "5115--5127",
    abstract = "Conversations on social media tend to go off-topic and turn into different and sometimes toxic exchanges. Previous work focuses on analysing textual dialogues that have derailed into toxic content, but the range of derailment types is much broader, including spam or bot content, tangential comments, etc. In addition, existing work disregards conversations that involve visual information (i.e. images or videos), which are prevalent on most platforms. In this paper, we take a broader view of conversation derailment and propose a new challenge: detecting derailment based on the {\textquotedblleft}change of conversation topic{\textquotedblright}, where the topic is defined by an initial post containing both a text and an image. For that, we (i) create the first Multimodal Conversation Derailment (MCD) dataset, and (ii) introduce a new multimodal conversational architecture (MMConv) that utilises visual and conversational contexts to classify comments for derailment. Experiments show that MMConv substantially outperforms previous text-based approaches to detect conversation derailment, as well as general multimodal classifiers. MMConv is also more robust to textual noise, since it relies on richer contextual information."
}