Review Sentiment Research Articles

What makes a better hotel selection? A hybrid approach considering tourists’ preference and review helpfulness

ABSTRACT Hotel selection is crucial in planning trips. Several studies constructed the decision methods, which assumed that people are completely rational and neglected decision-maker’s (DM’s) behavioural aspects, based on text reviews or numerical ratings with the subjective or objective weights of criteria. Therefore, this study proposes a picture fuzzy gained and lost dominance score (PF-GLDS) method based on prospect theory, which integrates user-generated text reviews and multi-criteria ratings to facilitate hotel selection while considering tourists’ preference and review helpfulness. First, review helpfulness is analyzed to enhance data quality. Second, a decision matrix is constructed by simultaneously considering sentiment in helpful text reviews as well as multi-criteria ratings. Third, the criteria are derived by the maximising deviation and best worst methods (BWM), respectively, for tourists’ preferred objective and subjective weights. Finally, to address hotel selection problems, an extended GLDS method with picture fuzzy information, considering bounded rationality behaviour, is developed. Empirical evaluation on five hotels from the TripAdvisor website demonstrates the reasonableness and advantages of our proposed hybrid approach in achieving more objective and reliable decision making. Concurrently, this study can serve as a reference for tourists seeking well-suited hotels and tourism website optimisation.

Hybrid Method for User Review Sentiment Categorization in ChatGPT Application Using N-Gram and Word2Vec Features

The rapid development of Artificial Intelligence (AI) has significantly influenced nearly all aspects of life. One AI product widely used by people worldwide is the Chat Generative Pre-Training Transformer (ChatGPT), which can respond to questions conversationally. Although data indicates that the use of ChatGPT in Indonesia is less widespread than in other countries, a Populix survey reveals that half of the respondents have utilized ChatGPT, using AI more than once a month. This indicates its crucial role among the Indonesian population. ChatGPT is not limited to browsers; it is also available as a downloadable application on the Google Play Store. The ChatGPT application has garnered various user reviews, particularly those from Indonesia. Therefore, this research employs the Naïve Bayes Classifier and K-Means Clustering to classify sentiments and group user reviews of the ChatGPT application originating from Indonesia. The study utilizes TF-IDF and Word2Vec as feature extraction methods, combining various N-Gram in data preprocessing to consider the context of sequentially arranged words that may carry meaning. The best classification results are obtained from the trigram classification model, as indicated by precision, recall, and accuracy values of 0.99 each, along with an F1-score of 1. Clustering also yields positive results, with some overlapping, yet words within clusters exhibit high similarity. Categorization results suggest that user reviews of the ChatGPT application from Indonesia tend to be positive, expressing satisfaction impressions, providing feedback for feature development, and expressing hope for the continued availability of the accessible version of ChatGPT due to its remarkable benefits.

Evaluation of the Effectiveness of Neural Network Models for Analyzing Customer Review Sentiments on Marketplace

According to the 2019 report, Tokopedia is the most visited marketplace with 140,000,000 visitors per month, making it one of the most popular marketplaces in Indonesia. Customers have the opportunity to write reviews about the products they purchase at the end of the transaction process on Tokopedia. The aim of this research is to conduct sentiment analysis on product reviews on Tokopedia. Three neural networks that will be used for text classification are Bi-GRU, GRU, and LSTM. The data processing technique is divided into training and testing samples, split into 80%:20% using the holdout technique. The BI-GRU algorithm has an accuracy of 0.93% and precision of 0.96, better than the other two methods LSTM and GRU, which each have an accuracy of 0.92 and recall of 0.91.

Airline reviews processing: Abstractive summarization and rating-based sentiment classification using deep transfer learning

Opinion summarization and sentiment classification are key processes for understanding, analyzing, and leveraging information from customer opinions. The rapid and ceaseless increase in big data of reviews on e-commerce platforms, social media, or review portals becomes a stimulus for the automation of these processes. In recent years, deep transfer learning has opted to solve many challenging tasks in Natural Language Processing (NLP) relieving the hassles of exhaustive training and the requirement of extensive labelled datasets. In this work, we propose frameworks for Abstractive Summarization (ABS) and Sentiment Analysis (SA) of airline reviews using Pretrained Language Models (PLM). The abstractive summarization model goes through two finetuning stages, the first one, for domain adaptation and the second one, for final task learning. Several studies in the literature empirically demonstrate that review rating has a positive correlation with sentiment valence. For the sentiment classification framework, we used the rating value as a signal to determine the review sentiment, and the model is built on top of BERT (Bidirectional Encoder Representations from Transformers) architecture. We evaluated our models comprehensively with multiple metrics. Our results indicate competitive performance of the models in terms of most of the evaluation metrics.

The world from the perspective of digital nomads: exploring sentiments in destination reviews

PurposeThis study aims to explore the emotional landscapes and spatial preferences of digital nomads, focusing on how sentiments expressed in destination reviews influence their mobility and destination choices.Design/methodology/approachEmploying a lexicon-based sentiment analysis of social media comments and reviews, alongside advanced geographical information systems (GIS) mapping techniques, the study analyzes the emotional tones that digital nomads associate with various destinations worldwide.FindingsThe analysis reveals significant patterns of emotional sentiments, with trust and joy being predominant in preferred destinations. Spatial patterns identified through GIS mapping highlight the global distribution of these sentiments, underscoring the importance of emotional well-being in destination choice.Practical implicationsInsights from this study offer valuable guidance for Destination Management Organizations (DMOs) in strategic planning, enhancing destination appeal through targeted marketing strategies that resonate with the emotional preferences of digital nomads.Originality/valueThis research introduces a novel approach by integrating sentiment analysis with GIS to map the emotional and spatial dynamics of digital nomadism, contributing a new perspective to the literature on tourism and mobility.

Evaluating a Company's Corporate Reputation from the Perspective of Its Employees by Analyzing Sentiment in Online Reviews

A comprehensive evaluation of an organization's performance throughout its existence is known as its corporate reputation (Kircova & Esen, 2018). Businesses with a good corporate reputation have a greater chance of influencing the attitudes and actions of their customers, giving them a competitive edge (Kircova, 2018). Because there are so many comments and opinions on the internet that are easily available to non-specialists, the evaluation of company reputation is becoming a more relevant topic in the field of business studies (Shayaa, 2018). In the past, surveys, sample groups, and qualitative interviews were considered reliable methods for assessing a company's reputation (Smith, 2010). Newburry and Fombrun & Fonzy have already brought attention to a novel approach to assessing a company's reputation. The invention of a reputation-measuring tool and a predictive model that shows how corporate reputation affects stakeholder outcomes were the main goals of Fombrun's most recent research (Fombrun, Fonzy, Newburry, 2015). Sentiment analysis using internet reviews as a means of assessing corporate reputation has not received much attention up to this point. In order to assess the reputation of the company, this study uses sentiment analysis as a suitable tool to look at the opinions that employees have about their firms. With our tool, businesses can respond to stakeholder requests and market changes in an efficient manner. Additionally, it might serve as a means of informing companies that are unaware of unfavorable internet reviews.

Arabic Sentiment Analysis Evaluation of Saudi Arabia's Telecommunication Using Several Deep Learning Algorithms

Sentiment analysis (SA) is a technique that applies natural language processing (NLP) in order to analyze and classify the emotion in sentiment reviews. SA is responsible for analyzing people's feelings, opinions, and experiences that are shared through the Internet and social networks. In this paper, we focus on investigating, evaluating, and improving Arabic sentiment analysis (ASA) models, datasets, and challenges. ASA has several difficulties, like language’s morphological features, many dialects, no clear and uniform corpora, low accuracy, and restricted ASA material. In order to do that, we do a full analysis and evaluation of Arabic sentiment analysis models and datasets that target e-marketing services such as telecommunication, health, and books. We evaluate our data set, called Sara, with several Arabic sentiment datasets in terms of brief description, dataset size, source of collecting data, field type, and abbreviation. We enhanced our previous models by using ensemble learning average techniques. The accuracy of our enhanced model has increased and now reaches around 97%. Also, we evaluate our developed ASA using deep learning (DL) algorithms with other ASA models in the field of e-marketing. Our models have significant improvements in terms of performance compared with other works, where our three models, CNN-Model, LSTM-Mode2, and CNN+LSTM-Model3, have accuracy of 96.83%, 94.74%, and 96.91%, respectively.

Online Reviews Sentiment Analysis Based on High-Rise Residential Projects in Malaysia

The Malaysian property industry has suffered due to increasing numbers of unsold properties, especially high-rise residential types. Industry practitioners believed the absence of accurate market data for developers caused a mismatch where the developer failed to provide the right properties for the market demand. Thus, a crucial need to understand public opinion on sentiment and preferences for high-rise property. This study derived an online-reviews-based process for evaluating public sentiment and preferences to understand the reason behind the imbalances of supply and demand currently faced by the property industry in Malaysia. The present study introduced an alternative approach to the evaluation of public sentiments and preferences towards high-rise residential via sentiment analysis and interpreted the cause of positive and negative opinions via Term Frequency-Inverse Document Frequency (TF-IDF) analysis. To demonstrate the applicability of the proposed approach, an experiment based on multiple high-rise properties as a case study. The findings are expected to be employed by developers/government in the evaluation of their weaknesses and strengths on the high-rise properties project and how developers/government can improve certain areas.

Sentiment Analysis Based on Travelers’ Reviews Using the SVM Model with Enhanced Conjunction Rule-Based Approach

Abstract: It is a tough task for tourism management to identify their user reviews and come up with solutions to the advancement of their tourism organizations. There are many social media reviews, and Tourism organizations face the challenge of evaluating numerous social media reviews to find solutions for advancing their organizations. It can be tough to physically assess all those reviews, social media has become a huge trend these days. People are constantly sharing their experiences and opinions on tourist places. By analyzing the sentiment of reviews, it may obtain useful information about the popularity of different tourist destinations. It's a great way to understand what people love about certain places. Sentiment classification is indeed a valuable tool in classifying reviews into different categories, aiding in decision-making. However, it's important to note that reviews often contain noisy content like typos and emoticons, which can affect the accuracy of the algorithms. Taking these aspects into consideration is crucial for achieving more accurate results. Decision-making and multiple class classification of reviews are possible with the application of sentiment classification. Sentiment analysis plays a crucial role in helping tourists make informed decisions about their travel destinations. In this particular paper, Using an Enhanced Conjunction Rule-Based Approach and Support Vector Machine (SVM) machine learning technique, the authors conducted sentiment analysis. They collected the dataset from different tourism review websites to train and evaluate their model. The findings of this paper are significant as they not only provide valuable insights in the field of tourism but also help in identifying the most appropriate algorithm for tourism-related analysis. The findings of this paper are significant as they not only provide valuable insights in the field of tourism but also help in identifying the most appropriate algorithm for tourism-related analysis. This information can greatly contribute to the development and improvement of tourism strategies and decision-making processes.

Movie Review Sentiment Analysis and AI-Story Generation Web Application

Abstract: This paper presents a web application designed to enhance the interaction between users and multimedia content through two innovative platforms: "MOVIE REVIEW SENTIMENT ANALYSIS" and "AI-STORY GENERATION." The first platform leverages the Fastai library and LSTM networks to perform sentiment analysis on user-submitted movie reviews, determining their polarity as positive or negative. This analysis directly influences the movie's aggregate rating, with the system capable of processing extensive textual input with high accuracy. Ratings are dynamically updated and stored in JSON format. The second platform, AI-STORY GENERATION, introduces a creative avenue for generating novel stories based on user prompts. It utilizes Natural Language Processing (NLP) techniques and a Generative Pretrained Transformer (GPT-2 Large) model, trained on tokenized movie scripts, to produce coherent and engaging narratives. The Flask web framework supports the application's backend, providing a robust and scalable foundation for user interaction and content delivery. This dual-platform approach not only demonstrates the practical application of advanced machine learning and NLP techniques in enhancing digital entertainment experiences but also showcases the potential for AI-driven tools to foster creative storytelling. The integration of sentiment analysis and story generation within a single application illustrates a novel use case of AI in the context of web-based entertainment, potentially paving the way for more personalized and interactive user experiences

Effect of Epoch Value on the Performance of the RNN-LSTM Algorithm in Classifying Lazada App Review Sentiments

In today's development, the process of buying and selling transactions between sellers and buyers is so developed. not only done directly but can also be done online or can be called e-commerce. Which is where the development of technology is so fast that it indirectly encourages entrepreneurs to develop through e-commerce. Lazada is one of the online stores in Indonesia that has many users and Lazada makes it easy to shop without the need to come to the place or directly. However, purchasing goods using e-commerce has problems regarding the quality of the goods you want to buy, therefore purchasing goods can be seen through reviews of each one you want to buy. Sentiment analysis is carried out using the Recurrent Neural Network (RNN) method with Long Short Term Memory (LSTM). And using the Epoch value as a parameter in processing validation data and test data to produce the best accuracy value

Analysis of TF-IDF and TF-RF Feature Extraction on Product Review Sentiment

Sentiment analysis of product reviews is critical in understanding customer views and satisfaction, especially in the context of e-commerce applications. A marketplace provides channels where users can submit reviews of the products they purchase. However, due to the large number of reviews in a marketplace, analyzing them is no longer feasible to be performed manually. This research proposes a machine learning implementation to perform sentiment analysis on product reviews. In this research, the product review dataset on Shopee marketplace is used for sentiment analysis by comparing TF-IDF and TF-RF feature extraction using the SVM algorithm with stages of dataset, labeling, feature extraction and accuracy results. The importance of the comparison between TF-IDF and TF-RF feature extraction in this research is related to the need to evaluate and determine which feature extraction method is most effective in increasing the accuracy of sentiment analysis. TF-IDF and TF-RF are two methods commonly used in text analysis, and a comparison of their performance can provide deep insight into the effectiveness of each in the context of product sentiment analysis.Thus, through this comparison, this research aims to determine the best approach that can provide the highest accuracy results, so that the results can serve as a guide for further research. Based on the evaluation, the highest accuracy value is achieved at 92.87% by using TF-IDF and SVM classifiers which outperformed previous research.

Machine Learning-Based Students’ Sentiment towards E-Learning amid COVID-19 Pandemic

The global COVID-19 pandemic has created exceptional difficulties for college and university students. With educational institutions shutting down and an abrupt shift to online learning, students are facing new challenges. Despite the advantages of e-learning, developing nations like Pakistan are experiencing major hurdles due to a lack of internet access and financial constraints. As a result, students' academic performance is being negatively impacted. Researchers are using sentiment analysis of social media platforms such as Facebook, Twitter, and YouTube to gain insight into student experiences during this challenging time. This study seeks to create a machine learning-based sentiment classification system that can determine the sentiment of higher education students in Pakistan towards e-learning classes during the COVID-19 pandemic. The primary objective of this research is to identify and categorize the challenges and problems that university students face in their e-learning classes. The research employed Multi-Nominal NB and Gaussian NB classifiers to examine the sentiment of online reviews and comments of students. We achieve 99% accuracy using Gaussian NB and 98% accuracy using Multinomial NB classifiers. According to the study's results, the COVID-19 epidemic has had a significant effect on the education system, with the vast majority of feedback being negative (70%). Only a small percentage of feedback was classified as neutral (29.9%) or positive (4%). This finding underscores the urgent need for better solutions for online learning during and after the pandemic. The study underscores the importance of addressing these unique challenges faced by students in developing countries during the pandemic. There is a pressing need for innovative solutions that can ensure that higher education remains effective and accessible in these challenging times. By utilizing sentiment analysis and machine learning, researchers can gain a better understanding of the experiences of students during this crisis. This understanding can inform targeted interventions and solutions that can improve academic performance and well-being for students in developing countries like Pakistan. The findings of this research provide important insights and recommendations for policymakers, educators, and stakeholders in the higher education sector.

Naïve Bayes Algorithm for Sentiment Analysis of Blibli.com Review on Google Play Store

Currently, there are approximately 354 million active mobile phones in Indonesia, placing the country fourth globally in terms of the highest number of mobile phone users. E-Commerce, as a form of online transaction, enables the digital exchange of goods and services to meet daily needs. This research aims to implement sentiment analysis using the Naive Bayes classification algorithm as a method to gather user opinions. Thus, the study not only provides insights into customer satisfaction with Blibli.com but also serves as a basis for potential improvements in services or feature development to enhance the online shopping experience. Overall, the Naive Bayes algorithm successfully achieved an accuracy of around 84%, demonstrating its proficiency in categorizing sentiment in reviews. When focusing on negative data, the Naive Bayes algorithm exhibited a precision of approximately 79%, recall of around 95%, and an f1-score of about 86%, indicating its success in identifying and classifying negative reviews with high precision and sensitivity. On the positive side, the Naive Bayes algorithm achieved a precision of about 91%, recall of around 83%, and an f1-score of about 87%.

Improved playstore review sentiment classification accuracy with stacking ensemble

In today's digital era, user reviews on the Playstore platform are an invaluable source of information for developers, offering insights that are critical for service improvement. Previous research has explored the application of stacking ensemble methods, such as in the context of predicting depression among university students, to enhance prediction accuracy. However, these studies often do not explicitly detail the data acquisition process, leaving a gap in understanding the applicability of these methods to different domains. This research aims to bridge this gap by applying the stacking ensemble approach to improve the accuracy of sentiment classification in Playstore reviews, with a clear exposition of the data collection method. Utilizing Logistic Regression as the meta classifier, this methodology is executed in several stages. Initially, data was collected from user reviews of online loan applications on Google Playstore, ensuring transparency in the data acquisition process. The data is then classified using three basic models: Random Forest, Naive Bayes, and SVM. The outputs of these models serve as inputs to the Logistic Regression meta model. A comparison of each base model output with the meta model was subsequently carried out. The test results on the Playstore review dataset demonstrated an increase in accuracy, precision, recall, and F1 score compared to using a single model, achieving an accuracy of 87.05%, which surpasses Random Forest (85.6%), Naive Bayes (85.55%), and SVM (86.5%). This indicates the effectiveness of the stacking ensemble method in providing deeper and more accurate insights into user sentiment, overcoming the limitations of single models and previous research by explicitly addressing data acquisition methods.

Artificial intelligence assisted insights into Bali’s destination image: sentiment and thematic analyses of TripAdvisor reviews

<p><span>This study applies sentiment and thematic content analyses based on natural language processing (NLP) to gain valuable insights into the perceived image of Bali as a tourist destination. This study addresses the gap in how to realize the benefits of big data analytics in applied research, by using more approachable tools for researchers with limited programming skills and coding experience. A total of 6,800 TripAdvisor reviews of Bali’s top 12 tourist attractions between May 2019 and April 2023 were scrapped. The authors used Bardeen.ai for data mining and Atlas.ti for qualitative data analyses. Sentiment analysis revealed an overwhelmingly positive sentiment (70.4%) towards Bali’s tourist attractions, indicating a positive destination image. Post-pandemic tourists tend to express more positive sentiments in their reviews compared to pre-pandemic. Thematic content analysis indicated that positive sentiments are strongly related to satisfaction, positive experiences, enjoyment, and excitement, while environmental concerns and dissatisfaction are potentially harmful to Bali’s destination image. The study provides valuable insights into tourists’ emotional sentiments, perceptions, and thematic patterns of behavior, which can inform tourism marketers and destination strategists, and contribute to the larger discussion of utilizing big data analytics in tourism marketing research.</span></p>

ANALISIS SENTIMEN ULASAN APLIKASI SHAZAM DI GOOGLE PLAY STORE MENGGUNAKAN SUPPORT VECTOR MACHINE

Shazam is a popular music recognition app on the Google Play Store. Shazam allows users to discover new songs and identify songs that are playing around them. In addition, it provides song lyrics, music videos, and song recommendations. User reviews give an idea of how users perceive the application, be it positive or negative. In this study, sentiment analysis was conducted on Shazam user reviews on the Google Play Store. The researchers used a Support Vector Machine (SVM) model to classify user reviews into two sentiments, namely positive and negative. Results show that SVM has 84% accuracy in predicting the sentiment of Shazam reviews. Furthermore, it can be shown that Shazam gets five times more positive responses than negative responses. Therefore, SVM is better at predicting positive reviews than negative reviews. This research can help interested parties to understand how users perceive the app as a whole.

A novel TODIM-based multi-attribute decision making method under information described by Z-numbers for selecting online B&B

This study designs a new TODIM-based multi-attribute decision making (MADM) method under information described by Z-numbers for selecting online Bed and Breakfast (B&B), which includes extracting the evaluation attributes and obtaining the best online B&B. To do that, first the fine-tuned Bidirectional Encoder Representation from Transformers (BERT) model is used to analyze the sentiment of all online reviews from nine regions of Airbnb, which these reviews about online B&Bs are divided into positive and negative comments. And then Term Frequency-Inverse Document Frequency (TF-IDF) is used to extract attribute feature words of positive and negative comments. Their intersection is sought to determine the attributes of the tourists' online B&B selection. Next, the ranking technique of Z-number and the distance of Z-number are put forward. Finally, a novel TODIM-based MADM method under information described by Z-numbers is proposed to select the B&Bs by the online review of B&Bs obtained from Ctrip.com. The advantage of this method is that it not only considers the reliability of online reviews, but also reflects the psychological factors of tourists. The feasibility of the proposed method is illustrated by ranking the B&Bs, and the flexibility and superiority of the method are highlighted by the sensitivity analysis and comparative analysis.

Movie sentiment analysis based on Long Short-Term Memory Network

An important task in the study of Natural Language Processing (NLP) is the analysis of movie reviews. It finishes the task of classifying movie review texts into sentiment, such as positive, negative or neutral sentiment. Previous works mainly follow the pipeline of LSTM (Long Short-Term Memory Network). The network model is a variant of Recurrent Neural Network (RNN) and particularly suitable for processing natural language texts. Though existing LSTM-based works have improved the performance significantly, we argue that most of them deal with the problem of analyzing the sentiment of movie reviews while ignore analyze the model performance in different application scenarios, such as different lengths of the reviews and the frequency of sentiment adverbs in the reviews. To alleviate the above issue, in this paper, we constructed a simple LSTM model containing an embedding layer, a batch normalization layer, a dropout layer, a one-dimensional convolutional layer, a maximal pooling layer, a bi-directional LSTM layer and a fully connected layer. We used the existing IMDB movie review dataset to train the model, and selected two research scenarios of movie review length and frequency of occurrence of sentiment adverbs to test the model, respectively. From the experimental results, we proposed a model for the scenarios in which the LSTM model handles the problem of sentiment analysis with respect to the dataset construction, model stability and generalization ability, text fragment processing, data preprocessing and feature extraction, model optimization and improvement.

Decoding sentiment: A sentiment analysis model for movie reviews

Sentiment analysis of movie reviews can provide valuable insights into movie reactions and preferences. To this end, this study proposes the Convolutional Long Short-Term Memory (ConvLSTM) neural network for movie review sentiment analysis. ConvLSTM can efficiently capture sequential information due to its recurrent neural network characteristics. Specifically, the movie review data are first tokenized. Next, the ConvLSTM analysis model is constructed additionally by fine-tuning its parameters to optimize the performance. The ConvLSTM model consists of multiple storage units that retain contextual information, enabling the model to identify long-distance dependencies in the text. The network is trained using a combination of positive and negative movie reviews, and the training process involves adjusting the model weights to minimize the classification error. Experimental results demonstrate the effectiveness of the proposed method in accurately predicting movie review sentiment. It outperforms traditional machine learning methods in sentiment analysis tasks. The findings demonstrate the potential of LSTM-based sentiment analysis in various applications such as movie recommendation systems and market research. This study's findings help advance the development of sentiment analysis techniques and are of great relevance in understanding and catering to audience preferences in the movie industry.