Abstract
We analyze the impact of using sentiment features in the prediction of movie review scores. The effort included the creation of a new lexicon, Expanded OntoSenticNet (EON), by merging OntoSenticNet and SentiWordNet, and experiments were made on the “IMDB movie review” dataset, with the three main approaches for sentiment analysis: lexicon-based, supervised machine learning and hybrids of the previous. Hybrid approaches performed the best, demonstrating the potential of merging knowledge bases and machine learning, but supervised approaches based on review embeddings were not far.- Anthology ID:
- 2022.salld-1.3
- Volume:
- Proceedings of the 2nd Workshop on Sentiment Analysis and Linguistic Linked Data
- Month:
- June
- Year:
- 2022
- Address:
- Marseille, France
- Venue:
- SALLD
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 9–18
- Language:
- URL:
- https://aclanthology.org/2022.salld-1.3
- DOI:
- Cite (ACL):
- João Ramos, Diogo Apóstolo, and Hugo Gonçalo Oliveira. 2022. Movie Rating Prediction using Sentiment Features. In Proceedings of the 2nd Workshop on Sentiment Analysis and Linguistic Linked Data, pages 9–18, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Movie Rating Prediction using Sentiment Features (Ramos et al., SALLD 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.salld-1.3.pdf
- Data
- ConceptNet, IMDb Movie Reviews