@inproceedings{purver-etal-2022-tracking,
    title = "Tracking Changes in {ESG} Representation: Initial Investigations in {UK} Annual Reports",
    author = "Purver, Matthew  and
      Martinc, Matej  and
      Ichev, Riste  and
      Lon{\v{c}}arski, Igor  and
      Sitar {\v{S}}u{\v{s}}tar, Katarina  and
      Valentin{\v{c}}i{\v{c}}, Aljo{\v{s}}a  and
      Pollak, Senja",
    editor = "Wan, Mingyu  and
      Huang, Chu-Ren",
    booktitle = "Proceedings of the First Computing Social Responsibility Workshop within the 13th Language Resources and Evaluation Conference",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2022.csrnlp-1.2",
    pages = "9--14",
    abstract = "We describe initial work into analysing the language used around environmental, social and governance (ESG) issues in UK company annual reports. We collect a dataset of annual reports from UK FTSE350 companies over the years 2012-2019; separately, we define a categorized list of core ESG terms (single words and multi-word expressions) by combining existing lists with manual annotation. We then show that this list can be used to analyse the changes in ESG language in the dataset over time, via a combination of language modelling and distributional modelling via contextual word embeddings. Initial findings show that while ESG discussion in annual reports is becoming significantly more likely over time, the increase varies with category and with individual terms, and that some terms show noticeable changes in usage.",
}