Does History Matter? Using Narrative Context to Predict the Trajectory of Sentence Sentiment

Liam Watson, Anna Jurek-Loughrey, Barry Devereux, Brian Murphy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

While there is a rich literature on the tracking of sentiment and emotion in texts, modelling the emotional trajectory of longer narratives, such as literary texts, poses new challenges. Previous work in the area of sentiment analysis has focused on using information from within a sentence to predict a valence value for that sentence. We propose to explore the influence of previous sentences on the sentiment of a given sentence. In particular, we investigate whether information present in a history of previous sentences can be used to predict a valence value for the following sentence. We explored both linear and non-linear models applied with a range of different feature combinations. We also looked at different context history sizes to determine what range of previous sentence context was the most informative for our models. We establish a linear relationship between sentence context history and the valence value of the current sentence and demonstrate that sentences in closer proximity to the target sentence are more informative. We show that the inclusion of semantic word embeddings further enriches our model predictions.
Original languageEnglish
Title of host publicationWProceedings of the orkshop on Linguistic and Neurocognitive Resources
Pages38-42
Number of pages5
Publication statusPublished - May 2020

Fingerprint Dive into the research topics of 'Does History Matter? Using Narrative Context to Predict the Trajectory of Sentence Sentiment'. Together they form a unique fingerprint.

  • Cite this

    Watson, L., Jurek-Loughrey, A., Devereux, B., & Murphy, B. (2020). Does History Matter? Using Narrative Context to Predict the Trajectory of Sentence Sentiment. In WProceedings of the orkshop on Linguistic and Neurocognitive Resources (pp. 38-42) https://www.aclweb.org/anthology/2020.lincr-1.5