A Lexicon-based Method to Determine Subjectivity of Unstructured Data

Mahoto, Naeem Ahmed; Khan, Sehar Gul; Ruk, Sadaquat Ali

doi:10.1109/imtic.2018.8467271

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The result is evaluated using three different datasets. The experimental results have also been compared with expert opinions to evaluate the significance of the proposed lexicon-based subjectivity detection sentiment analyzer [18]. However, this approach is solely a lexicon-based approach for classification.…”

Section: Sentiment Analysis With Subjectivity Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Sentiment Attribution Analysis With Hierarchical Classification and Automatic Aspect Categorization on Online User Reviews

Win

Ravana²,

Shuib³

2022

MJCS

View full text Add to dashboard Cite

Due to COVID-19 pandemic, most physical business transactions were pushed online. Online reviews became an excellent source for sentiment analysis to determine a customer's sentiment about a business. This insight is valuable asset for businesses, especially for tourism sector, to be harnessed for business intelligence and craft new marketing strategies. However, traditional sentiment analysis with flat classification and manual aspect categorization technique imposes challenges with non-opinionated reviews and outdated pre-defined aspect categories which limits businesses to filter relevant opinionated reviews and learn new aspects from reviews itself for aspect-based sentiment analysis. Therefore, this paper proposes sentiment attribution analysis with hierarchical classification and automatic aspect categorization to improve the social listening for diligent marketing and recommend potential business optimization to revive the business from surviving to thriving after this pandemic. Hierarchical classification is proposed using hybrid approach. While automatic aspect categorization is constructed with semantic similarity clustering and applied enhanced topic modelling on opinionated reviews. Experimental results on two real-world datasets from two different industries, Airline and Hotel, shows that the sentiment analysis with hierarchical classification outperforms the classification accuracy with a good F1-score compared to baseline papers. Automatic aspect categorization was found to be able to unhide the sentiment of the aspects which was not recognized in manual aspect categorization. Although it is accepted that the effectiveness of aspect-based sentiment analysis on flat classification and manual aspect categorization, none have assessed the effectiveness while using hierarchical classification with a hybrid approach and automatic aspect categorization.

show abstract

Section: Sentiment Analysis With Subjectivity Classificationmentioning

confidence: 99%

“…Recently, [37] conducted a research on hierarchical classification using a rule-based approach on Twitter dataset. In this research, lexicon-based approach for subjectivity detection is used with a dictionary and corpus-based methods (SentiWordNet, Word-based corpus, Context-based corpus).…”

Section: Research Gap and Findingsmentioning

confidence: 99%

Sentiment Attribution Analysis With Hierarchical Classification and Automatic Aspect Categorization on Online User Reviews

Win

Ravana²,

Shuib³

2022

MJCS

View full text Add to dashboard Cite

show abstract

Sentiment Analysis on Covid-19 Vaccination Using Machine Learning Techniques

Bhalerao¹,

Naiknaware²,

Manza³

et al. 2023

Advances in Computer Science Research

View full text Add to dashboard Cite

In this research work, we have performed Machine Learning and Lexicon Based Techniques to identify and analyze user's expression or opinion on covid-19 vaccination from social media platform that is Twitter and acquainted the bulk tweets from 01 June 2021 to August 2021 using various twitter hashtags. Machine learning based Classifiers are used for investigating the evaluation performance of Algorithms. Real time datasets and machine Learning Algorithms are compared with Best Data classification Evaluation based on the size of train data also another approach is to investigating the polarity by using Lexicon Based approach for this Bing Liu Lexicons and Stanford University Lexicons are used. The global pandemic has created the medical emergency and stops the many regular activities. The whole world in the lockdown or quarantine to because Coronavirus disease. Among them, Covaxin, Covishield, Pfizer, Moderna and SputnikVare popular. Universally publicare articulating opinions on protection and success of the vaccines on social media. Research article shows, such tweets are collected from developer Application Management using a Twitter API. Unprocessed tweets are kept and preprocessed through Machine Learning techniques. Users opinion are predicted using a Classifiers Decision Tree, Support Vector Machine, K NN Algorithm and Naïve Bayes. Comparative machine learning classifiers study here comparative analysis is got highest accuracy of 97% for Decision tree with Covaxin dataset, Support vector machine with 94% for SputnikV, Naïve Bayes got highest accuracy of 95 for Covishield dataset and KNN got Highest accuracy of 96% for Covaxin. The Lexicon Based polarity classifies the score into three users opinions, positive, negative, and neutral. Result shows that, Covaxin shows 28.

show abstract

A Lexicon-based Method to Determine Subjectivity of Unstructured Data

Cited by 2 publications

References 23 publications

Sentiment Attribution Analysis With Hierarchical Classification and Automatic Aspect Categorization on Online User Reviews

Sentiment Attribution Analysis With Hierarchical Classification and Automatic Aspect Categorization on Online User Reviews

Sentiment Analysis on Covid-19 Vaccination Using Machine Learning Techniques

Contact Info

Product

Resources

About