Contextual Sentence Classification: Detecting Sustainability Initiatives in Company Reports
This work addresses the need for automated analysis of sustainability efforts in corporate documents, which is incremental as it builds on existing text classification techniques for a specific domain.
The paper tackles the problem of detecting sustainability initiatives in company reports by introducing a new task and dataset, and proposes a model that uses sequences of consecutive sentences for classification, achieving results evaluated with a novel methodology.
We introduce the novel task of detecting sustainability initiatives in company reports. Given a full report, the aim is to automatically identify mentions of practical activities that a company has performed in order to tackle specific societal issues. New methods for identifying continuous sentence spans need to be developed for capturing the multi-sentence structure of individual sustainability initiatives. We release a new dataset of company reports in which the text has been manually annotated with sustainability initiatives. We also evaluate different models for initiative detection, introducing a novel aggregation and evaluation methodology. Our proposed architecture uses sequences of consecutive sentences to account for contextual information when making classification decisions at the individual sentence level.