Check the preview of 2nd version of this platform
being developed by the open MLCommons taskforce on automation and reproducibility
as a free, open-source and technology-agnostic on-prem platform.
Review highlights: opinion mining on reviews: a hybrid model for rule selection in aspect extraction
lib:e9dbe7b1ff4b83bb (v1.0.0)
Authors: Amit Kushwaha,Shubham Chaudhary
Where published: IML ’17, October 17–18, 2017, Liverpool, United Kingdom 2017 10
Document: PDF DOI
Artifact development version: GitHub
Abstract URL: https://dl.acm.org/citation.cfm?id=3158385
This paper proposes a methodology to extract key insights from user generated reviews. This work is based on Aspect Based Sentiment Analysis (ABSA) which predicts the sentiment of aspects mentioned in the text documents. The extracted aspects are fine-grained for the presentation form known as Review Highlights. The syntactic approach for extraction process suffers from the overlapping chunking rules which result in noise extraction. We introduce a hybrid technique which combines machine learning and rule based model. A multi-label classifier identifies the effective rules which efficiently parse aspects and opinions from texts. This selection of rules reduce the amount of noise in extraction tasks. This is a novel attempt to learn syntactic rule fitness from a corpus using machine learning for accurate aspect extraction. As the model learns the syntactic rule prediction from the corpus, it makes the extraction method domain independent. It also allows studying the quality of syntactic rules in a different corpus.
Where published: IML ’17, October 17–18, 2017, Liverpool, United Kingdom 2017 10
Document: PDF DOI
Artifact development version: GitHub
Abstract URL: https://dl.acm.org/citation.cfm?id=3158385
This paper proposes a methodology to extract key insights from user generated reviews. This work is based on Aspect Based Sentiment Analysis (ABSA) which predicts the sentiment of aspects mentioned in the text documents. The extracted aspects are fine-grained for the presentation form known as Review Highlights. The syntactic approach for extraction process suffers from the overlapping chunking rules which result in noise extraction. We introduce a hybrid technique which combines machine learning and rule based model. A multi-label classifier identifies the effective rules which efficiently parse aspects and opinions from texts. This selection of rules reduce the amount of noise in extraction tasks. This is a novel attempt to learn syntactic rule fitness from a corpus using machine learning for accurate aspect extraction. As the model learns the syntactic rule prediction from the corpus, it makes the extraction method domain independent. It also allows studying the quality of syntactic rules in a different corpus.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)