Amazon Review Data Research Articles

HGATT_LR: transforming review text classification with hypergraphs attention layer and logistic regression

Text classification plays a major role in research such as sentiment analysis, opinion mining, and customer feedback analysis. Text classification using hypergraph algorithms is effective in capturing the intricate relationships between words and phrases in documents. The method entails text preprocessing, keyword extraction, feature selection, text classification, and performance metric evaluation. Here, we proposed a Hypergraph Attention Layer with Logistic Regression (HGATT_LR) for text classification in the Amazon review data set. The essential keywords are extracted by utilizing the Latent Dirichlet Allocation (LDA) technique. To build a hypergraph attention layer, feature selection based on node-level and edge-level attention is assessed. The resultant features are passed as an input of Logistic regression for text classification. Through a comparison analysis of different text classifiers on the Amazon data set, the performance metrics are assessed. Text classification using hypergraph Attention Network has been shown to achieve 88% accuracy which is better compared to other state-of-the-art algorithms. The proposed model is scalable and may be easily enhanced with more training data. The solution highlights the utility of hypergraph approaches for text classification as well as their applicability to real-world datasets with complicated interactions between text parts. This type of analysis will empower the business people will improve the quality of the product.

A multiview clustering framework for detecting deceptive reviews

Online reviews, which play a key role in the ecosystem of nowadays business, have been the primary source of consumer opinions. Due to their importance, professional review writing services are employed for paid reviews and even being exploited to conduct opinion spam. Posting deceptive reviews could mislead customers, yield significant benefits or losses to service vendors, and erode confidence in the entire online purchasing ecosystem. In this paper, we ferret out deceptive reviews originated from professional review writing services. We do so even when reviewers leverage a number of pseudonymous identities to avoid the detection. To unveil the pseudonymous identities associated with deceptive reviewers, we leverage the multiview clustering method. This enables us to characterize the writing style of reviewers (deceptive vs normal) and cluster the reviewers based on their writing style. Furthermore, we explore different neural network models to model the writing style of deceptive reviews. We select the best performing neural network to generate the representation of reviews. We validate the effectiveness of the multiview clustering framework using real-world Amazon review data under different experimental scenarios. Our results show that our approach outperforms previous research. We further demonstrate its superiority through a large-scale case study based on publicly available Amazon datasets.

A content-based collaborative filtering algorithm for movies and TVS recommendation

With the rapid development of multimedia technology and the constant upgrading of film and television libraries, users' demand for movies and television is increasing. How to accurately and timely find favorite movies from massive movie and television resources according to user's preferences and needs has become a great challenge. In recent years, the recommendation of movies and TVs has attracted a lot of research interest from academia and industry. The existing recommendation algorithms mainly include content based and collaborative filtering. The former recommends projects through collaborative learning of others' interests, while the content-based method examines the rich context of the project. In this paper, to further improve the performance of recommendations, a content based collaborative filtering method is proposed to provide recommendations for movies and television. Specifically, we extract and vectorize feature and category information from movies based on TF-IDF and apply truncated SVD to reduce the dimensions of the rating and TF-IDF matrix to retain the most representative information. We calculate the cosine similarity between the vectors from these two matrices. The final recommendation is to list 10 movies based on the average similarity of content and ratings. Extensive experiments on Amazon review data have proven the effectiveness of this method.

Research on accuracy analysis and improvement of recommender system based on amazon review

Recommender system is a system that uses artificial intelligence and data mining technology to recommend items or services that meet users' preferences based on their historical behaviors and interests. In modern society, people are faced with more and more choices, and the emergence of recommender system can help users filter out valuable content from complex information and improve user satisfaction and experience. In this paper, collaborative filtering is used to implement a recommender system based on Amazon review data set. Meanwhile, Singular Value Decomposition (SVD) and Principal Component Analysis (PCA) are used to conduct dimensionality reduction and other operations on the data. Root Mean Squared Error (RMSE) A value expressed as a recommendation for accuracy. After the establishment of the recommender system and three precision analysis experiments, it achieves this by applying a selected filtering algorithm to the input supplied, which is frequently in the form of user reviews of products.

A Comparative Study of Sentiment Analysis Methods for Detecting Fake Reviews in E-Commerce

The popularity of the e-commerce system has increased, especially under the COVID scenario. Consumer product reviews from the past have had a significant impact on influencing consumers' purchasing decisions. Fake reviews—those written by humans and computers that engage in dishonest behavior—are consequently generated to increase product sales. The fake reviews hurt consumers and are dishonest. The goal of this research is to examine and evaluate the performance of various methods for identifying fake reviews. The well-known and widely-used Amazon Review Data (2018) dataset was used for this research. The first 10 product categories on Amazon.com with favorable feedback will be provided in the data section. After that, perform fundamental data preparation procedures such as special character trimming, bag of words, TF-IDF, etc. The models are trained to create a dataset for detecting fake reviews. This research compares the performance of four different models: GPT-2, NBSVM, BiLSTM, and RoBERTa. The hyperparameters of the models are also tuned to find the optimal values. The research concludes that the RoBERTa model performs the best overall, with an accuracy of 97%. GPT-2 has an overall accuracy of 82%, NBSVM has an overall accuracy of 95%, and BiLSTM has an overall accuracy of 92%. The research also calculates the Area Under the Curve (AUC) for each model and finds that RoBERTa has an AUC of 0.9976, NBSVM has an AUC of 0.9888, BiLSTM has an AUC of 0.9753, and GPT-2 has an AUC of 0.9226. It can be observed that the RoBERTa model has the highest AUC value, which is close to 1. Therefore, it can be concluded that this model provides the most accurate prediction for detecting fake reviews, which is the main focus of this research. Doi: 10.28991/HIJ-2023-04-02-08 Full Text: PDF

TaskDrop: A competitive baseline for continual learning of sentiment classification

In this paper, we study the multi-task sentiment classification problem in the continual learning setting, i.e., a model is sequentially trained to classify the sentiment of reviews of products in a particular category. The use of common sentiment words in reviews of different product categories leads to large cross-task similarity, which differentiates it from continual learning in other domains. This knowledge sharing nature renders forgetting reduction focused approaches less effective for the problem under consideration. Unlike existing approaches, where task-specific masks are learned with specifically presumed training objectives, we propose an approach called Task-aware Dropout (TaskDrop) to randomly sample a binary mask for each task. While the standard dropout generates and applies random masks for each training instance per epoch for regularization, random masks in TaskDrop are used for model capacity allocation and reuse to each coming task. We conducted experimental studies on Amazon review data and made comparison to various baselines and state-of-the-art approaches. Our empirical results show that regardless of simplicity, TaskDrop overall achieved competitive performance, especially after relatively long term learning. This demonstrates that the proposed random capacity allocation mechanism works well for continual sentiment classification.

Impact on recommendation performance of online review helpfulness and consistency

PurposeThe existing collaborative filtering algorithm may select an insufficiently representative customer as the neighbor of a target customer, which means that the performance in providing recommendations is not sufficiently accurate. This study aims to investigate the impact on recommendation performance of selecting influential and representative customers.Design/methodology/approachSome studies have shown that review helpfulness and consistency significantly affect purchase decision-making. Thus, this study focuses on customers who have written helpful and consistent reviews to select influential and representative neighbors. To achieve the purpose of this study, the authors apply a text-mining approach to analyze review helpfulness and consistency. In addition, they evaluate the performance of the proposed methodology using several real-world Amazon review data sets for experimental utility and reliability.FindingsThis study is the first to propose a methodology to investigate the effect of review consistency and helpfulness on recommendation performance. The experimental results confirmed that the recommendation performance was excellent when a neighbor was selected who wrote consistent or helpful reviews more than when neighbors were selected for all customers.Originality/valueThis study investigates the effect of review consistency and helpfulness on recommendation performance. Online review can enhance recommendation performance because it reflects the purchasing behavior of customers who consider reviews when purchasing items. The experimental results indicate that review helpfulness and consistency can enhance the performance of personalized recommendation services, increase customer satisfaction and increase confidence in a company.

Financial Incentives Dampen Altruism in Online Prosocial Contributions: A Study of Online Reviews

This paper uses a large Amazon review data set to examine the impact of financial incentives on prosocial contributions. The econometric analyses demonstrate a significant spillover effect, where product reviewers, after experiencing the receipt of financial incentives, tend to produce more positive but lower-quality unincentivized reviews subsequently. Theoretically, this paper advances our understanding of the interplay between financial incentives and prosocial behaviors through the lens of self-determination theory. Practically, this study provides insights into the design of online prosocial communities. Managers should not be enticed solely by an immediate increase in contribution quantity because the increased contribution volume might come at the cost of decreased quality in future unincentivized contributions. If platforms decide to provide financial incentives, they should target only altruistic contributors and limit the amount of incentives that an individual can receive. These findings provide important managerial implications for platforms hoping to motivate users’ prosocial contributions.

Resource management for model learning at entity level

Many current and future applications plan to provide entity-specific predictions. These range from individualized healthcare applications to user-specific purchase recommendations. In our previous stream-based work on Amazon review data, we could show that error-weighted ensembles that combine entity-centric classifiers, which are only trained on reviews of one particular product (entity), and entity-ignorant classifiers, which are trained on all reviews irrespective of the product, can improve prediction quality. This came at the cost of storing multiple entity-centric models in primary memory, many of which would never be used again as their entities would not receive future instances in the stream. To overcome this drawback and make entity-centric learning viable in these scenarios, we investigated two different methods of reducing the primary memory requirement of our entity-centric approach. Our first method uses the lossy counting algorithm for data streams to identify entities whose instances make up a certain percentage of the total data stream within an error-margin. We then store all models which do not fulfil this requirement in secondary memory, from which they can be retrieved in case future instances belonging to them should arrive later in the stream. The second method replaces entity-centric models with a much more naive model which only stores the past labels and predicts the majority label seen so far. We applied our methods on the previously used Amazon data sets which contained up to 1.4M reviews and added two subsets of the Yelp data set which contain up to 4.2M reviews. Both methods were successful in reducing the primary memory requirements while still outperforming an entity-ignorant model.

Electronic word-of-mouth marketing on Amazon: Exploring how and to what extent Amazon reviews affect sales

Consumers today base many of their decisions on peer referrals and online reviews. With the omnipresence of social media and online reviews, electronic word-of-mouth marketing (eWOM) has become a priority for many companies for both business growth and reputational management. The objective of this study is to examine the effectiveness of eWOM and its impact on sales. This study also seeks to help organizational leaders understand the significance of eWOM and its role in effective consumer and stakeholder relations, and in overall brand management. The researchers of this project explored eWOM by examining Amazon reviews from two different Kickstarter companies to determine which elements of online reviews impact product sales. By overlaying Amazon review data and sales figures from each Kickstarter company, researchers were able to determine the review factors that companies should focus on to increase their sales and grow their brands. The results of this study show that products with a high volume of positive reviews made by verified purchasers positively correlate to product sales.
 
 Keywords: electronic word-of-mouth marketing, Amazon, online reviews, Kickstarter, sales, reputational management, brand reputation, online reputation management

Exploratory Data Analysis using Python

Data need to be analyzed so as to produce good result. Using the result decision can be taken. For example recommendation system, ranking of the page, demand fore casting, prediction of purchase of the product. There are some leading companies where the review of the customer plays a great role to analyze the factor which influences the review rating. We have used exploratory data analysis (EDA) where data interpretations can be done in row and column format. We have used python for data analysis. it is object oriented ,interpreted and interactive programming language. it is open source with rich sets of libraries like pandas, MATplotlib, seaborn etc. We have used different types of charts and various types of parameter to analyze Amazon review data sets which contains the reviews of electronic data items. We have used python programming for the data analysis.

Unsupervised Domain Adaptation With Adversarial Residual Transform Networks.

Domain adaptation (DA) is widely used in learning problems lacking labels. Recent studies show that deep adversarial DA models can make markable improvements in performance, which include symmetric and asymmetric architectures. However, the former has poor generalization ability, whereas the latter is very hard to train. In this article, we propose a novel adversarial DA method named adversarial residual transform networks (ARTNs) to improve the generalization ability, which directly transforms the source features into the space of target features. In this model, residual connections are used to share features and adversarial loss is reconstructed, thus making the model more generalized and easier to train. Moreover, a special regularization term is added to the loss function to alleviate a vanishing gradient problem, which enables its training process stable. A series of experiments based on Amazon review data set, digits data sets, and Office-31 image data sets are conducted to show that the proposed ARTN can be comparable with the methods of the state of the art.

Who will stay with the brand after posting non-5/5 rating of purchase? An empirical study of online consumer repurchase behavior

Customer retention has been fully examined in marketing research. It has been noticed that satisfied customers do not always retain and customer churn happens repeatedly in an e-Business context. In this paper, we focus on online consumer repurchase behavior on online business to consumer platforms after posting a non-5/5 rating of the purchased product. The non-5/5 rating can be taken as buyer’s self-claimed non-fully satisfaction on shopping experience. We investigate whether online consumers’ self-claimed non-fully satisfied shopping experience of a brand would attenuate their repurchase intention of the same brand, and further, what factors would impact their repurchase frequency and the time interval to the next purchase of this brand. We applied multinomial logit regression and ordinary least square regressions to Amazon review data to test the research hypotheses. We collected more than 241 thousand review records involving over 182 thousand buyers of Amazon beauty products. 44% of these buyers rated below 5, and 19% out of whom had repurchase records. The empirical results showed that consumers’ past shopping experience and the non-5/5 rating level significantly impact the possibility of repurchase intention; consumers’ emotional stability is associated with their repurchase frequency positively; their relationship proneness to a certain brand shortens the time interval to the next purchase of the brand. Managerial implications and future research directions are discussed last.

Multi-task learning using a hybrid representation for text classification

Text classification is an important task in machine learning. Specifically, deep neural network has been shown strong capability to improve performance in different fields, for example speech recognition, objects recognition and natural language processing. However, in most previous work, the extracted feature models do not achieve the relative text tasks well. To address this issue, we introduce a novel multi-task learning approach called a hybrid representation-learning network for text classification tasks. Our method consists of two network components: a bidirectional gated recurrent unit with attention network module and a convolutional neural network module. In particular, the attention module allows for the task learning private feature representation in local dependence from training texts and that the convolutional neural network module can learn the global representation on sharing. Experiments on 16 subsets of Amazon review data show that our method outperforms several baselines and also proves the effectiveness of joint learning multi-relative tasks.

Multi-task learning using variational auto-encoder for sentiment classification

With the rapid growth of the big data, many approaches in the representation of text for sentiment classification have been successfully proposed in natural language processing. However, these approaches remedy this problem based on single-task supervised objectives learning and do not consider their relative of multiple tasks. Based on these defects, in this work, we consider these tasks are relative, and use weight-shared parameters for learning the representation of text in neural network model, we introduce and study a multi-task approach with variational auto-encoder generative model (MTVAE) by jointly learning them. Experimental results on six subsets of Amazon review data show that the proposed approach can effectively improve the sentiment classification accuracy by other relative tasks.

An analysis of review content and reviewer variables that contribute to review helpfulness

Review helpfulness is attracting increasing attention of practitioners and academics. It helps in reducing risks and uncertainty faced by users in online shopping. This study examines uninvestigated variables by looking at not only the review characteristics but also important indicators of reviewers. Several significant review content and two reviewer variables are proposed and an effective review helpfulness prediction model is built using stochastic gradient boosting learning method. This study derived a mechanism to extract novel review content variables from review text. Six popular machine learning models and three real-life Amazon review data sets are used for analysis. Our results are robust to several product categories and along three Amazon review data sets. The results show that review content variables deliver the best performance as compared to the reviewer and state-of-the-art baseline as a standalone model. This study finds that reviewer helpfulness per day and syllables in review text strongly relates to review helpfulness. Moreover, the number of space, aux verb, drives words in review text and productivity score of a reviewer are also effective predictors of review helpfulness. The findings will help customers to write better reviews, help retailers to manage their websites intelligently and aid customers in their product purchasing decisions.

Comprehensive Study on Lexicon-based Ensemble Classification Sentiment Analysis

We propose a novel method for counting sentiment orientation that outperforms supervised learning approaches in time and memory complexity and is not statistically significantly different from them in accuracy. Our method consists of a novel approach to generating unigram, bigram and trigram lexicons. The proposed method, called frequentiment, is based on calculating the frequency of features (words) in the document and averaging their impact on the sentiment score as opposed to documents that do not contain these features. Afterwards, we use ensemble classification to improve the overall accuracy of the method. What is important is that the frequentiment-based lexicons with sentiment threshold selection outperform other popular lexicons and some supervised learners, while being 3–5 times faster than the supervised approach. We compare 37 methods (lexicons, ensembles with lexicon’s predictions as input and supervised learners) applied to 10 Amazon review data sets and provide the first statistical comparison of the sentiment annotation methods that include ensemble approaches. It is one of the most comprehensive comparisons of domain sentiment analysis in the literature.