Opinion mining and sentiment analysis on online customer review

Kumar, K L Santhosh; Desai, Jayanti; Majumdar, Jharna

doi:10.1109/iccic.2016.7919584

Cited by 72 publications

(29 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A lexicon is a special dictionary in which words are assigned to sentiment scores. 39,46 The main advantage is that, once a lexicon is built, a fast unsupervised sentiment classification is achieved, by summing the overall word scores. Thus, there is no need for labeled data.…”

Section: Related Workmentioning

confidence: 99%

Social Media Cross-Source and Cross-Domain Sentiment Classification

Zola

Cortez

Ragno

et al. 2019

Int. J. Info. Tech. Dec. Mak.

View full text Add to dashboard Cite

Due to the expansion of Internet and Web 2.0 phenomenon, there is a growing interest in sentiment analysis of freely opinionated text. In this paper, we propose a novel cross-source cross-domain sentiment classification, in which cross-domain-labeled Web sources (Amazon and Tripadvisor) are used to train supervised learning models (including two deep learning algorithms) that are tested on typically nonlabeled social media reviews (Facebook and Twitter). We explored a three-step methodology, in which distinct balanced training, text preprocessing and machine learning methods were tested, using two languages: English and Italian. The best results were achieved using undersampling training and a Convolutional Neural Network. Interesting cross-source classification performances were achieved, in particular when using Amazon and Tripadvisor reviews to train a model that is tested on Facebook data for both English and Italian.

show abstract

Section: Related Workmentioning

confidence: 99%

Social Media Cross-Source and Cross-Domain Sentiment Classification

Zola

Cortez

Ragno

et al. 2019

Int. J. Info. Tech. Dec. Mak.

View full text Add to dashboard Cite

show abstract

“…Precision and recall are the major performance measures of a supervised learning model. The precision gives the proportion of positive predictions which are truly positive, recall gives the proportion of true positive cases over the positive cases [21].…”

Section: Performance -Evaluationmentioning

confidence: 99%

Opinion Mining and Client Feedback Mining for Quality Improvement

Chandra,

Gyaderla,

Lakshmi

et al. 2019

IJEAT

View full text Add to dashboard Cite

As E-Commerce growing rapidly, now a day’s customers reviews about product has become most crucial for development of the business. The opinion mining is most crucial in ecommerce websites, furthermore advantageous with client’s feedback. The current research work mainly focuses on the client engagement review analysis. In this paper we concentrated on mining reviews from clients who are seeking consulting services from the IT industries, which enables the companies to understand the data patterns and identify some Key Performance Indicators and develop accordingly. The Client feedback mining allows the user to allow Clients to convey what they think and feel about the services. This opinion or review about the product will help purchaser to get an idea regarding the product, and the seller regarding required improvements or updates, hence opinion mining plays a major role in ecommerce. We also concentrated on the sentimental analysis that means a reviewer can write about the product positively or negatively, it depends on many parameters such as emotions they want to express, opinion of the product they purchased, received time, package and condition they received the product. It clearly gives an idea to the seller and purchaser about demand, supply and quality improvement. Key Performance Indicator is measured based on metrics that business organizations track in order to measure their progress towards goal within marketing networks. We designed a mathematical model and executed for results. We discussed different algorithms based on opinion mining and we implemented cloud based practical implementation of a simulated model for understanding of results and given graphical analysis along with result analysis

show abstract

“…At [5], proposes an approach namely Latent Semantic Analysis (LSA) for product feature identification, which is a method to inspect links between the terms contained in a document, thus extracts the feature terms from a then formed concurrency matrix. At [6], the paper compares approaches for opinion classification using Naive Bayes Classification, Logistic Regression and making use of SentiWordNet, coming to the conclusion that Naive Bayes was more efficient among the three at classification. The [7], paper outlines a step-by-step procedure for sentiment analysis and summarization of a customer review with the steps being, 1. Review Collection 2.…”

Section: Related Workmentioning

confidence: 99%

Sentiment Analysis and Opinion Summarization of Product Feedback

2019

ijrte

View full text Add to dashboard Cite

With the exponential growth of online shopping platforms, user interaction is made direct through their reviews and ratings. User’s opinions and experiences are a significant source of valuable information in decision making process. In recent days, almost every website encourages users to express and exchange their views, suggestions and opinions related to product, services, policies, etc. publicly. Opinion mining is an extensive branch of Artificial Intelligence and a form of Natural Language Processing which illustrates the attitude of the customers, in specific services or products. Also known as Sentiment Analysis, it aims at determining the response and mood or attitude of the speaker or the overall contextual and emotional polarity or reaction. Existing algorithms determine sentiment by training on datasets, lexicon-based approach by calculating polarity and rule-based approach for classification. Opinion Summarization is the process of consolidating a large amount of sentiments and opinions into a clear and brief statement for an easier grasp on the underlying context. Major summarization methods include, Extractive method, Sentence Ranking, Abstractive method and Clustering of Textual Segments. Hence it is important to judge and classify these reviews and present a laconic opinion so it would be easier for users to obtain a gist and overall polarity on the various reviews instead of going through all of them

show abstract

Opinion mining and sentiment analysis on online customer review

Cited by 72 publications

References 4 publications

Social Media Cross-Source and Cross-Domain Sentiment Classification

Social Media Cross-Source and Cross-Domain Sentiment Classification

Opinion Mining and Client Feedback Mining for Quality Improvement

Sentiment Analysis and Opinion Summarization of Product Feedback

Contact Info

Product

Resources

About