Product Reviews Research Articles

Empowering Retail Dual Transformer-Based Profound Product Recommendation Using Multi-Model Review

Advancements in technology have significantly changed how we interact on social media platforms, where reviews and comments heavily influence consumer decisions. Traditionally, opinion mining has focused on textual data, overlooking the valuable insights present in customer-uploaded images—a concept we term Multus-Medium. This paper introduces a multimodal strategy for product recommendations that utilizes both text and image data. The proposed approach involves data collection, preprocessing, and sentiment analysis using Vti for images and SpanBERT for text reviews. These outputs are then fused to generate a final recommendation. The proposed model demonstrates superior performance, achieving 91.55% accuracy on the Amazon dataset and 90.89% on the Kaggle dataset. These compelling findings underscore the potential of our approach, offering a comprehensive and precise method for opinion mining in the era of social media-driven product reviews, ultimately aiding consumers in making informed purchasing decisions.

CNN-Based Models for Emotion and Sentiment Analysis Using Speech Data

The study aims to present an in-depth Sentiment Analysis (SA) grounded by the presence of emotions in the speech signals. Nowadays, all kinds of web-based applications ranging from social media platforms and video-sharing sites to e-commerce applications provide support for Human–Computer Interfaces (HCIs). These media applications allow users to share their experiences in all forms such as text, audio, video, GIF, and so on. The most natural and fundamental form of expressing oneself is through speech. Speech-Based Sentiment Analysis (SBSA) is the task of gaining insights into speech signals. It aims to classify the statement as neutral, negative, or positive. On the other hand, Speech Emotion Recognition (SER) categorizes speech signals into the following emotions: disgust, fear, sadness, anger, happiness, and neutral. It is necessary to recognize the sentiments along with the profoundness of the emotions in the speech signals. To cater to the above idea, a methodology is proposed defining a text-oriented SA model using the combination of CNN and Bi-LSTM techniques along with an embedding layer, applied to the text obtained from speech signals; achieving an accuracy of 84.49%. Also, the proposed methodology suggests an Emotion Analysis (EA) model based on the CNN technique highlighting the type of emotion present in the speech signal with an accuracy measure of 95.12%. The presented architecture can also be applied to different other domains like product review systems, video recommendation systems, education, health, security, and so on.

A Study on the Identification of the Water Army to Improve the Helpfulness of Online Product Reviews

Based on the perspective of identifying the water army, this paper uses the methods of machine learning and data visualization to analyze the helpfulness of online produce reviews, portray product portraits, and provide real and helpful product reviews. In order to identify and eliminate the water army, the Term Frequency-Inverse Document Frequency Model (TF-IDF) and Latent Semantic Index Model (LSI) are used. After eliminating the water army, three classification methods were selected to perform sentimental analysis, including logistics, SnowNLP, and Convolutional Neural Network for text(TextCNN). The TextCNN has the highest F1 score among the three classification methods. At the same time, the Latent Dirichlet Allocation mode (LDA) is used to extract the topics of various reviews. Finally, targeted countermeasures are proposed to manufacturers, consumers, and regulators.

Scientific knowledge in the 21st century on social and economic factors that influence mortality due to tuberculosis: A bibliometric review

This research presents a bibliometric review of scientific production on the social and economic factors that influence mortality from tuberculosis between the years 2000 and 2024. The analysis covered 1742 documents from 848 sources, revealing an annual growth of 6% in scientific production with a notable increase starting in 2010, reaching a peak in 2021. This increase reflects growing concern about socioeconomic inequalities affecting tuberculosis mortality, exacerbated in part by the COVID-19 pandemic. The main authors identified in the study include Naghavi, Basu and Hay, whose works have had a significant impact on the field. The most prominent journals in the dissemination of this research are Plos One, International Journal of Tuberculosis and Lung Disease and The Lancet. The countries with the greatest scientific production include the United States, the United Kingdom, India and South Africa, highlighting a strong international contribution and a global approach to the problem. The semantic development of the research shows a concentration on terms such as “mortality rate”, “risk factors” and “public health”, with a thematic map highlighting driving themes such as “socioeconomic factors” and “developing countries”. The theoretical evolution reflects a growing interest in economic and social aspects to gender contexts and associated diseases. This study provides a comprehensive view of current scientific knowledge, identifying key trends and emerging areas for future research.

Fruit Wastes and Crop Residues as Nutrient Sources for Bacterial Nanocellulose Production: A Review

Nanocellulose has been developed and used as a bio-based advanced material in modern biotechnology. Lately, bacterial nanocellulose (BNC) emerged as a prominent biopolymer because of its multi-functional application in various industries, such as food, biomedical, cosmetics, and environmental. The emerging concern for large-scale BNC production is the high fermentation costs, low productivity, and expensive culture medium. To minimise this issue, agro-industrial wastes can be used as feedstock. Recently, many studies have investigated the utilization of agro-industrial wastes as potential nutrient sources for BNC production. However, a comprehensive review of BNC production from fruit wastes and crop residues is lacking. To address this gap, the current review focuses on the utilization of fruit wastes and crop residues for BNC production, including its advantages and disadvantages. This study contributes to the scientific community by (a) providing an insight into fruit waste and crop residue utilization for BNC synthesis (b) an overview on its advantages and disadvantages (c) providing recommendations and future perspectives on BNC production from agro-industrial waste utilization. The sustainable concept of BNC production utilizing agro-industrial wastes opens a way for industries to produce BNC on a larger scale.

A text sentiment analysis method based on BiGRU and capsule network

Most of the existing sentiment analysis methods based on product review texts rarely consider the aspect features of the review texts, and the relevant analysis models do not consider the long-term contextual dependency features and local text features at the same time, thus affecting the accuracy of sentiment analysis. A text sentiment analysis method based on a bidirectional gated recurrent network (BiGRU) and a capsule network is proposed. This method first uses a word frequency statistics-based method to extract the aspect features of the review text and integrates them into the word vector representation, thereby effectively improving the expressive power of the word vector. Then, BiGRU is used to extract the long-term contextual dependency features of the text, and the capsule network is used to extract the local features of the text, thereby achieving high-precision text sentiment analysis based on aspects. Experimental results on real datasets show that the proposed method is superior to existing sentiment analysis models such as bidirectional long short-term memory network (BiLSTM), CNN-LSTM, and TextCNN in terms of evaluation indicators such as accuracy, precision, recall, and score.

The Influence of Consumer Product Knowledge, Trust, and Risk Perception on Purchase Intention Among Shopee Consumers: The Role of Reviews as a Moderating Variable

The development of e-commerce has changed consumer behavior. With the presence of e-commerce, many habits have changed, starting from previous shopping habits in offline stores, now switching to shopping at online stores using shopping sites and applications such as Shopee, because it makes it easier for consumers to make buying and selling transactions online. However, Shopee, which is a consumer favorite, has several problems, including some consumers who buy products at Shopee feeling disappointed because the goods purchased do not match expectations, thus affecting consumer buying intentions. Several previous studies have shown that there is a relationship between consumer trust and purchasing decisions. This study uses descriptive quantitative research using multiple linear regression analysis. The subjects of this research are Shopee consumers. The variables used in this study are consumer product knowledge, trust, risk perception and reviews as moderating variables. The results of the research show that consumer product knowledge has a positive but not significant effect on Shopee consumers’ purchasing decisions. Meanwhile, the variables of trust, risk perception and reviews have a significant positive effect on Shopee consumers’ purchase intentions. Then the review variable is not able to moderate the relationship between consumer product knowledge and purchase intention. However, reviews are able to moderate the relationship between trust, risk perception and purchase intention.

Strategic Communication of Shopee Affiliators on TikTok for Consumer Engagement

Background: The rise of social media has transformed marketing strategies, particularly in e-commerce. Specific Background: This study examines how affiliate marketers on TikTok enhance consumer engagement and purchasing decisions. Knowledge Gap: Limited understanding exists regarding the specific communication strategies that TikTok affiliates use to influence consumer perceptions. Aims: The research analyzes the communication concepts employed by a TikTok affiliate account to attract consumers. Results: Findings reveal that product reviews by creators serve as credible sources of information, reducing consumer uncertainty and building trust. Novelty: This study offers unique insights into the dynamics of affiliate marketing on TikTok, highlighting benefits for both creators and store owners through authentic promotions. Implications: The research emphasizes the importance of effective communication in affiliate marketing, suggesting that these strategies not only enhance consumer trust but also facilitate organic campaigns that expand market reach with minimal advertising costs. Highlights : Credible Information: Product reviews by creators help reduce consumer uncertainty. Trust Building: Honest evaluations foster stronger relationships between creators and audiences. Organic Reach: Effective communication strategies enhance marketing campaigns without high advertising costs. Keywords: TikTok, Affiliate, Marketing, Consumer, Trust

On the Interaction Between Cheap-Talk Advertising and Credible Product Reviews

This paper investigates the interaction between cheap-talk advertising and credible third-party product reviews to inform customers about product quality. We find that cheap-talk advertising can be informative when the firm’s private information helps predict a credible product review. A more informative credible product review has two effects on cheap-talk advertising. First, a credible product review plays a disciplinary role that enables the firm to provide informative advertising. Second, it reduces the incremental value of cheap-talk advertising. We find that, in equilibrium, whether or not the advertising is consistent with a credible product review is informative about product quality. The results also imply that an overly informative product review can reduce the total information available to customers by deterring the firm from providing informative advertising.

Hybrid HAN‐CNN with aspect term extraction for sentiment analysis using product review

AbstractIn this article, an intensive sentiment analysis approach termed Hierarchical attention‐convolutional neural network (HAN‐CNN) has been proposed using product reviews. Firstly, the input product review is subjected to Bidirectional Encoder Representation from Transformers (BERT) tokenization, where the input data of each sentence are partitioned into little bits of words. Thereafter, Aspect Term Extraction (ATE) is carried out and feature extraction is completed utilizing some features. Finally, sentiment analysis is accomplished by the developed HAN‐CNN, which is formed by combining a Hierarchical Attention Network (HAN) and a Convolutional Neural Network (CNN). Moreover, the proposed HAN‐CNN achieved a greater performance with maximum accuracy, recall and F1‐Score of 91.70%, 90.60% and 91.20%, respectively.

An emerging market? The European Maritime Industry’s View on Autonomous Maritime Systems: A Survey

Abstract Autonomous Maritime Systems have significantly emerged in maritime research over the past decade. But how is this technology adapted by the maritime industry in business applications? Based on a product and application-focused literature review as well as an industrial survey among 52 companies, this paper gives insights into the industrial’s interest in this emerging technology for different maritime segments, their prioritized use cases as well as the main barriers for the emerging market according to the European Maritime Industry. Hereby, it assesses the technology adoption rate specifically for different segments, i.e. Ship Operators, Manufacturers, Ports, Shipbuilding, Offshore and (Hinterland) logistics.

Unlocking TikTok’s Formula: Video Length, Tags, and Beauty Content Success

With the rapid growth of TikTok in the digital era, beauty influencers have gained significant influence over consumer decisions, particularly through makeup product reviews. TikTok’s short and interactive content style has brought attention to how video characteristics such as length and the number of tags affect engagement metrics like views, likes, and comments. This research explores the impact of these factors using data analysis from a sample of 25 TikTok videos, where the average video length was 2 minutes and 20 seconds, and the top 25% of videos had lengths exceeding 3 minutes and 30 seconds. The findings reveal that longer videos tend to foster deeper engagement by providing more comprehensive reviews, with the top 25% of videos achieving 30% higher engagement than the average. Additionally, a higher number of tags significantly increases video reach. These insights are valuable for influencers and marketers looking to optimize their content strategies, particularly in the beauty industry, where maximizing audience engagement is crucial.

The Influence of Content Marketing, Brand Ambassadors and Product Reviews on Purchasing Decisions for Scarlett Whitening Consumers in Pekanbaru City

This study was conducted to determine the effect of content marketing, brand ambassadors, and product reviews on purchasing decisions for Scarlett Whitening consumers in Pekanbaru City. With 190 responders the population in examination was Scarlett Whitening in Pekanbaru City. Purposive and non-probability sampling techniques are used in sample dedicating. Multiple linear regression analysis is the analytical technique utilized in this research, and SPSS V.25 helpline to process the data. Research findings indicate that content marketing has a partial effect on purchasing decisions, brand ambassadors has a partial effect on purchasing decisions, product reviews has a partial effect on purchasing decisions. In addition, there is a simultaneous relationship betweeen content marketing, brand ambassadors, and product reviews and purchasing decisions

The Influence of Service Quality and Brand Image on Customer Satisfaction and Customer Loyalty at the Pratama Marga Ayu Clinic in Badung, Bali

This research investigates the impact of service quality and brand image on customer satisfaction and customer loyalty at the Pratama Marga Ayu Clinic in Badung, Bali. Using SPSS and Smart-PLS for analysis, the study reveals that both service quality and brand image significantly and positively affect customer satisfaction, which in turn influences customer loyalty. Additionally, customer satisfaction mediates the relationship between service quality and customer loyalty. The findings highlight the importance of enhancing service quality and brand image to foster higher customer satisfaction and loyalty. The research concludes with practical suggestions for improving service and brand image, including increasing healthcare personnel, enhancing branding efforts, and implementing customer loyalty programs. Future studies are recommended to explore other influencing factors such as product reviews, location, and social media marketing to further enrich the understanding of customer decision-making.

Aspect based sentiment analysis of Twitter mobile phone reviews using LSTM and Convolutional Neural Network

The proliferation of online shopping has led to a surge in product reviews, providing valuable information to consumers. However, the overwhelming volume and subjective nature of these reviews make it difficult to assess product performance accurately. We propose a machine learning-based system that extracts sentiment from online reviews to address this challenge. Our system effectively identifies positive, negative, and neutral sentiments and classifies sentiment for specific product aspects. By offering concise and clear information, our system empowers consumers to make informed purchasing decisions and assists manufacturers in improving their products. Our proposed LSTMCNN model, trained on a dataset of 62,563 reviews, achieved impressive results with an accuracy of 95.84%, precision of 95.6% and recall of 95.8%. This significantly outperforms existing models, demonstrating the effectiveness of our approach. Moving forward, we aim to further enhance the accuracy of our system, track sentiment changes over time, and develop personalized product recommendations. These advancements will continue to increase the value and utility of online reviews in e-commerce.

Harnessing the Power of Web Scraping and Machine Learning to Uncover Customer Empathy from Online Reviews

In today's information-driven world, companies need to grasp customer sentiment and pinpoint key product features to make informed choices and improve customer satisfaction. The abundance of online customer feedback provides businesses with a rich source of information about customer perceptions and preferences. Yet manual analysis of large volumes of reviews is a tedious and resource-intensive task. It describes a web scraping application that sorts reviews into positive, negative, or neutral sentiments that businesses can use for insight. By assigning weights to reviews based on perceived impact, the approach offers a nuanced understanding of customer opinions. Experimental results demonstrate its effectiveness in accurately categorizing and analysing reviews, distinguishing between genuine and fake feedback. Additionally, AI-powered examination of product reviews employs NLP methods to extract important information from customer feedback, identifying particular elements that customers like or find troubling. After the successful identification of gain points, they can be used to improvise product development and marketing. So, product-specific focused crawler is developed to extract customer reviews from the most trusted websites. As a side chain, this can also be used as a tool for analysing the competitors’ products to understand their pain as well as gain points. The approach can uncover the most discussed aspects of products, enabling businesses to better understand customer perceptions and preferences to make better decisions thereby saving time and money.

Speech errors in Internet product reviews as a marker of population literacy

Speech errors in Internet product reviews as a marker of population literacy

Peer Review and Natural-Like Social Relations of Production in Academia

ABSTRACT There is a paucity of studies addressing the nature of the social relations of production prevailing in academia prior to the commodification of academic research. By filling that gap, this paper enables us to better understand the historical presuppositions from which the process of knowledge commodification in academia has evolved. Our theoretically informed analysis will focus on peer review, given that it is one of the few academic practices where traces of that historical past can still be found. On the basis of Marx’s exposition of the main features of pre-capitalist social relations of production in the Grundrisse, it will be concluded that peer review reveals that social relations of production in academia were of a pre-capitalist, or natural-like, nature: peer review is labour of a direct nature; is the practice through which the academic community mediates its own reproduction, determining how – and, sometimes, if – its members enter into contact with the objective conditions of production; finally, in this latter capacity, peer review presupposes that the academic community relates to the conditions of knowledge production as though they were their collective property. These findings are employed to account for the underlying logics of the ongoing ‘functional transformation’ of peer review.

Singlet Oxygen in Photodynamic Therapy.

Photodynamic therapy (PDT) is a therapeutic modality that depends on the interaction of light, photosensitizers, and oxygen. The photon absorption and energy transfer process can lead to the Type II photochemical reaction of the photosensitizer and the production of singlet oxygen (1O2), which strongly oxidizes and reacts with biomolecules, ultimately causing oxidative damage to the target cells. Therefore, 1O2 is regarded as the key photocytotoxic species accountable for the initial photodynamic reactions for Type II photosensitizers. This article will provide a comprehensive review of 1O2 properties, 1O2 production, and 1O2 detection in the PDT process. The available 1O2 data of regulatory-approved photosensitizing drugs will also be discussed.

The Applicability of Principal Component Analysis: A Review of the Nigeria Gross Domestic Products (GDP)

In 2014, Nigeria was largest and fastest growing economy in Africa, and this is determine by year on year Gross Domestic Product (GDP), which is the major tools use by the rest of the world to determine the capacity of a country. Furthermore National Bureau of Statistics (NBS) releases both quarterly and yearly growth of Nigeria GDP, while the data source in this project is from NBS, starting from 1980 to 2017. Moreover the Nigeria GDP comprises many components. The major PCs use are Agriculture, Building and Construction, Industry, Wholesale and Retail Trade, and Services. It was observed that there is yearly growth in Nigeria gross domestic products due to increase in all contributors factored components from 1980 to 2017, Agriculture had the highest number activities to this per capital income followed by Industry, Services, wholesale and retail trade, and building and construction. Also the overall accumulated variance for the GDP for the studied period is 10.7 for a 56% coefficient of variation. All the contributors (Agriculture, Industry,......) maintained a positive correlation all through the period of study expect for Services that affect/shirk the GDP along the year. Wholesales experienced the strongest doling of taking care of the GDP with 98%, followed by Building and Construction, industry and agriculture with 86%, 78% and 6% respectively. However for Nigeria to maintain the largest economy in Africa It will strongly advice that the economy team should look properly on agriculture and industry and if this two increases certainly wholesale and retail trade with building and construction will be affected positively while extended to services, therefore the GDP will also be stabilise.