Multi-entity sentiment analysis using entity-level feature extraction and word embeddings approach

Colm Sweeney, Deepak Padmanabhan

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

6 Citations (Scopus)

Abstract

The sentiment analysis task has been traditionally divided into lexicon or machine learning approaches, but recently the use of word embeddings methods have emerged, that provide powerful algorithms to allow semantic understanding without the task of creating large amounts of annotated test data. One problem with this type of binary classification, is that the sentiment output will be in the form of '1' (positive) or '0' (negative) for the string of text in the tweet, regardless if there are one or more entities referred to in the text. This paper plans to enhance the word embeddings approach with the deployment of a sentiment lexicon-based technique to appoint a total score that indicates the polarity of opinion in relation to a particular entity or entities. This type of sentiment classification is a way of associating a given entity with the adjectives, adverbs, and verbs describing it, and extracting the associated sentiment to try and infer if the text is positive or negative in relation to the entity or entities.

Original languageEnglish
Title of host publicationInternational Conference on Recent Advances in Natural Language Processing
Subtitle of host publicationMeet Deep Learning, RANLP 2017 - Proceedings
EditorsRuslan Mitkov, Irina Temnikova, Kalina Bontcheva, Ivelina Nikolova, Galia Angelova
PublisherAssociation for Computational Linguistics
Pages733-740
Number of pages8
Volume2017-September
ISBN (Electronic)9789544520489
DOIs
Publication statusPublished - 01 Jan 2017
Event11th International Conference on Recent Advances in Natural Language Processing, RANLP 2017 - Varna, Bulgaria
Duration: 02 Sept 201708 Sept 2017

Conference

Conference11th International Conference on Recent Advances in Natural Language Processing, RANLP 2017
Country/TerritoryBulgaria
CityVarna
Period02/09/201708/09/2017

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Multi-entity sentiment analysis using entity-level feature extraction and word embeddings approach'. Together they form a unique fingerprint.

Cite this