eprintid: 14384 rev_number: 20 eprint_status: archive userid: 5 dir: disk0/00/01/43/84 datestamp: 2017-02-15 09:16:09 lastmod: 2021-08-27 17:28:33 status_changed: 2017-09-01 11:11:07 type: book_section metadata_visibility: show item_issues_count: 1 creators_name: Rekabsaz, N. creators_name: Lupu, M. creators_name: Baklanov, A. creators_name: Hanbury, A. creators_name: Duer, A. creators_name: Anderson, L. creators_id: 2067 creators_orcid: 0000-0003-1599-3618 title: Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models ispublished: pub divisions: prog_asa abstract: Volatility prediction--an essential concept in financial markets--has recently been addressed using sentiment analysis methods. We investigate the sentiment of annual disclosures of companies in stock markets to forecast volatility. We specifically explore the use of recent Information Retrieval (IR) term weighting models that are effectively extended by related terms using word embeddings. In parallel to textual information, factual market data have been widely used as the mainstream approach to forecast market risk. We therefore study different fusion methods to combine text and market data resources. Our word embedding-based approach significantly outperforms state-of-the-art methods. In addition, we investigate the characteristics of the reports of the companies in different financial sectors. date: 2017 date_type: published publisher: Association for Computational Linguistics id_number: 10.18653/v1/P17-1157 creators_browse_id: 22 full_text_status: public publication: ArXiv volume: 1 place_of_pub: Vancouver, Canada pagerange: 1712-1721 refereed: TRUE book_title: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics coversheets_dirty: FALSE fp7_project: no fp7_type: info:eu-repo/semantics/bookPart citation: Rekabsaz, N., Lupu, M., Baklanov, A. ORCID: https://orcid.org/0000-0003-1599-3618 , Hanbury, A., Duer, A., & Anderson, L. (2017). Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. pp. 1712-1721 Vancouver, Canada: Association for Computational Linguistics. 10.18653/v1/P17-1157 . document_url: https://pure.iiasa.ac.at/id/eprint/14384/1/1702.01978.pdf