Determining the sentiment of opinions
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
A survey on sentiment detection of reviews
Expert Systems with Applications: An International Journal
Identifying claimed knowledge updates in biomedical research articles
ACL '12 Proceedings of the Workshop on Detecting Structure in Scholarly Discourse
A three-way perspective on scientific discourse annotation for knowledge extraction
ACL '12 Proceedings of the Workshop on Detecting Structure in Scholarly Discourse
Hi-index | 0.00 |
We propose a model for knowledge attribution and epistemic evaluation in scientific discourse, consisting of three dimensions with different values: source (author, other, unknown); value (unknown, possible, probable, presumed true) and basis (reasoning, data, other). Based on a literature review, we investigate four linguistic features that mark different types epistemic evaluation (modal auxiliary verbs, adverbs/adjectives, reporting verbs and references). A corpus study on two biology papers indicates the usefulness of this model, and suggest some typical trends. In particular, we find that matrix clauses with a reporting verb of the form 'These results suggest', are the predominant feature indicating knowledge attribution in scientific text.