We innovate by transforming textual communications into actionable insights
We develop tools that aggregate textual data into innovative yet practical and understandable index solutions, tracking the authors’ sentiments about the topic of interest. We seek to continuously improve the understanding of the multi-dimensional textual information out there. Our ambitious goal is to grasp the stream of emotional content and its implications for society even faster than the impressive speed at which it is generated.
We are an international group of researchers with a passion for solving challenging problems at the intersection of textual analysis, sentiment mining, and econometrics. We deliver the same high quality for the sentometrics-branded services as for the white-labeled advisory and development. We prioritize excellence and progress, but always cut loose with that regular dose of fun.
Text-based forecasting: Improvement when the design of the textual aggregation method is optimized: Intratext, across-text and across-time weighting
- Boudt, K., & Thewissen, J. (2019). Jockeying for position in CEO letters: Impression management and sentiment analytics. Financial Management, 48, 77-115.
- Ardia, D., Bluteau, K., & Boudt, K. (20xx). Questioning the news about economic growth: Sparse forecasting using thousands of news-based sentiment values. International Journal of Forecasting, forthcoming.
Impact analysis: Modeling of heterogeneity in the impact of textual sentiment based measures on financial performance
- Arslan-Ayaydin, Ö., Boudt, K., & Thewissen, J. (2016). Managers set the tone: Equity incentives and the tone of earnings press releases. Journal of Banking & Finance, 72, S132-S147.
- Boudt, K., Thewissen, J., & Torsin, W. (2018). When does the tone of earnings press releases matter?. International Review of Financial Analysis, 57, 231-245.
- Ardia, D., Bluteau, K., & Boudt, K. (2018). Media and the stock market. A CAT and CAR analysis.
- Algaba, A., Borms, S., & Boudt, K. (20xx). Timeliness of ESG reputation from texts. In progress.
Network analysis: Modeling dependence across textual sentiment
- Ardia, D. Borms, S., & Boudt, K. (2018) Sentiment comovement and article features. In progress.
Software development: R package sentometrics
- Ardia, D., Bluteau, K., Borms, S., & Boudt, K. (2017). The R package sentometrics to compute, aggregate and predict with textual sentiment.