Aspect Based Sentiment Analysis in E-Commerce User Reviews Using Latent Dirichlet Allocation (LDA) and Sentiment Lexicon

Wahyudi, Eko; Kusumaningrum, Retno

doi:10.1109/icicos48119.2019.8982522

Cited by 12 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, the study gave an accuracy value of 92.15%. In another research [10], Eko Wahyudi conducted an aspect-based sentiment analysis on e-commerce reviews using LDA and Sentiment Lexicon. Based on three experiments conducted, it was found that the accuracy value of each experiment had an increase in value of 0.82%.…”

Section: Introductionmentioning

confidence: 99%

Multi-aspect sentiment analysis on netflix application using latent dirichlet allocation and support vector machine methods

Abelard

Sibaroni

2021

J.INFOTEL

View full text Add to dashboard Cite

Among many film streaming platforms that have sprung up, Netflix is the platform that has the most subscribers compared to the other platforms. However, not all reviews provided by the Netflix users are good reviews. These reviews will later be analyzed to determine what aspects are reviewed by the users based on reviews written on the Google Play Store, using the Latent Dirichlet Allocation (LDA) method. Then, the classification process using the Support Vector Machine (SVM) method will be carried out to determine whether each of these reviews is included in the positive or negative class (Sentiment Analysis). There are 2 scenarios that were carried out in this study. The first scenario resulted that the best number of LDA topics to be used is 40, and the second scenario resulted that the use of filtering process in the preprocessing stage reduces the score of the f1-score. Thus, this study resulted in the best performance score on LDA and SVM testing with 40 topics, and without running the filtering process with the score of 78.15%.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-aspect sentiment analysis on netflix application using latent dirichlet allocation and support vector machine methods

Abelard

Sibaroni

2021

J.INFOTEL

View full text Add to dashboard Cite

show abstract

“…In order to measure the effective information contained in the relevant description text and evaluate the host pre-interaction ability, we need to find semantic associations from texts, discover the rules of words in texts and achieve the goal of extracting effective information from unstructured texts. 74 Therefore, we need to use topic analysis to mine structured information. 75 Common topic models include LSA, PLSA and LDA models, while the LDA model can better detect the relationship between documents than others.…”

Section: Methodsmentioning

confidence: 99%

Improving hosts’ pre-interaction capabilities for sustainability based on Airbnb host content emergence characteristics

Wang

Jin

2022

Indoor and Built Environment

View full text Add to dashboard Cite

The sharing of accommodation as a sustainable environmental solution for the lodging market is prevalent all over the world. However, the rapid expansion and low occupancy rate could be due to the accommodation hosts’ lack of attention to the pre-interaction content while reducing their carbon footprint, which have caused a significant impact on guests’ decision-making and prevented sharing accommodation. To improve the host pre-interaction capabilities and achieve the environmentally friendly potential of sharing accommodation, this research aims to explore the host expression characteristics including important topics and keywords of host pre-interaction content from a symbolic interaction perspective. Conducting the latent Dirichlet allocation machine learning model, keywords clustering characteristics emerged as main topics based on 38,814 listings from Airbnb in Beijing. The result of investigating the features in these topics and the word distribution in three types of properties shows that in a homogenous accommodation community, hosts who make the pre-interaction have more orders than those who do not. At the same time, the focus of hosts on expressing explicit and abundant topic symbols can effectively increase the attractiveness of their listings. However, accommodation hosts who just post a long text but do not emphasize listing key topics would not convince guests to use the accommodation. A variety of practical implications of findings has been discussed for sharing accommodation practitioners to answer the challenge of sustainability.

show abstract

“…LDA is very widely used in the commercial fields. For example, Wahyudi and Kusumaningrum [8] have used an LDA-based topic model to perform sentiment analysis on user reviews of online shopping malls in Indonesia in their study.…”

Section: Introductionmentioning

confidence: 99%

User review analysis of dating apps based on text mining

Shen

Han

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

With the continuous development of information technology, more and more people have become to use online dating apps, and the trend has been exacerbated by the COVID-19 pandemic in these years. However, there is a phenomenon that most of user reviews of mainstream dating apps are negative. To study this phenomenon, we have used topic model to mine negative reviews of mainstream dating apps, and constructed a two-stage machine learning model using data dimensionality reduction and text classification to classify user reviews of dating apps. The research results show that: firstly, the reasons for the current negative reviews of dating apps are mainly concentrated in the charging mechanism, fake accounts, subscription and advertising push mechanism and matching mechanism in the apps, proposed corresponding improvement suggestions are proposed by us; secondly, using principal component analysis to reduce the dimensionality of the text vector, and then using XGBoost model to learn the low-dimensional data after oversampling, a better classification accuracy of user reviews can be obtained. We hope These findings can help dating apps operators to improve services and achieve sustainable business operations of their apps.

show abstract

Aspect Based Sentiment Analysis in E-Commerce User Reviews Using Latent Dirichlet Allocation (LDA) and Sentiment Lexicon

Cited by 12 publications

References 9 publications

Multi-aspect sentiment analysis on netflix application using latent dirichlet allocation and support vector machine methods

Multi-aspect sentiment analysis on netflix application using latent dirichlet allocation and support vector machine methods

Improving hosts’ pre-interaction capabilities for sustainability based on Airbnb host content emergence characteristics

User review analysis of dating apps based on text mining

Contact Info

Product

Resources

About