@inproceedings{ceron-etal-2022-optimizing,
    title = "Optimizing text representations to capture (dis)similarity between political parties",
    author = "Ceron, Tanise  and
      Blokker, Nico  and
      Pad{\'o}, Sebastian",
    editor = "Fokkens, Antske  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.conll-1.22/",
    doi = "10.18653/v1/2022.conll-1.22",
    pages = "325--338",
    abstract = "Even though fine-tuned neural language models have been pivotal in enabling {\textquotedblleft}deep{\textquotedblright} automatic text analysis, optimizing text representations for specific applications remains a crucial bottleneck. In this study, we look at this problem in the context of a task from computational social science, namely modeling pairwise similarities between political parties. Our research question is what level of structural information is necessary to create robust text representation, contrasting a strongly informed approach (which uses both claim span and claim category annotations) with approaches that forgo one or both types of annotation with document structure-based heuristics. Evaluating our models on the manifestos of German parties for the 2021 federal election. We find that heuristics that maximize within-party over between-party similarity along with a normalization step lead to reliable party similarity prediction, without the need for manual annotation."
}