Using Opinionated-Objective Terms to Improve Lexicon Based Sentiment Analysis

Bayode Ogunleye, Teresa Brunsdon, Tonderai Maswera, Laurie Hirsch, Jotham Gaudoin

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBNpeer-review

Abstract

Sentiment analysis (SA) has received huge attention to understand customer perception, especially in the movie review (IMDB) domain. This is due to the availability of large, labelled dataset. This has enhanced the use and development of machine learning (ML) algorithms ranging from the traditional machine learning algorithms, deep learning algorithms to large language models. The ML models have shown great performances. However, the application of ML methods for SA is limited in service industry like banking, due to the unavailability of large training dataset. Thus, we consider the use of lexicon-based sentiment analysis appropriate. We employ 346,000 Nigeria bank customers’ tweets to develop our corpus and thus, propose SentiLeye, a novel lexicon-based algorithm for sentiment analysis. Our algorithm incorporates corpus-based approach and external lexical resources for sentiment lexicon generation of Pidgin English language terms (a
non-English under resourced language). Moreover, we demonstrate the use of verbs and adverbs that express opinion on service experience to improve the performance of lexicon-based sentiment analysis. Results show that SentiLeye outperforms popular off-the-shelf sentiment lexicons with macro F1 score of 76%. We conclude that results from domain specific algorithms such as SentiLeye evidence that general purpose lexicons cannot replace them.
Original languageEnglish
Title of host publicationProceedings of the 12th International Conference on Soft Computing for Problem Solving
Subtitle of host publicationSocProS 2023, Volume 2
EditorsMillie Pant, Kusum Deep, Atulya Nagar
Place of PublicationSingapore
PublisherSpringer
Pages1-23
Number of pages17
Volume2
ISBN (Electronic)9789819732920
ISBN (Print)9789819732913
DOIs
Publication statusPublished - 1 Jul 2024
EventSoft Computing for Problem Solving: Moving Towards Society 5.0 - Indian Institute of Technology, Roorkee, India
Duration: 11 Aug 202313 Aug 2023
Conference number: 12th
http://www.socpros2023.iitr.ac.in/

Publication series

NameLecture Notes in Networks and Systems
PublisherSpringer
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceSoft Computing for Problem Solving
Abbreviated titleSocProS 2023
Country/TerritoryIndia
CityRoorkee
Period11/08/2313/08/23
Internet address

Bibliographical note

Not yet published

Fingerprint

Dive into the research topics of 'Using Opinionated-Objective Terms to Improve Lexicon Based Sentiment Analysis'. Together they form a unique fingerprint.

Cite this