Customer Reviews Research Articles

The Influence Of Storytelling, Social Media Marketing, and Customer Reviews Of Coffee Roasters On The Purchase Decision Of Single-Origin Arabica Coffee Beans By Coffee Shops

The coffee industry, centered on Arabica and Robusta beans, relies heavily on coffee shops for delivering quality products, particularly single-origin Arabica coffee. Coffee roasters, operating in the B2B market, supply coffee shops, shaping product quality and customer satisfaction. This study examines the impact of marketing strategies—storytelling, social media, and customer reviews—on coffee shop owners' decisions to purchase Arabica beans. Utilizing a quantitative approach with 222 respondents and multiple linear regression analysis in SPSS, findings show a significant positive influence of these strategies on purchase decisions. Together, they explain 70.6% of the variance, with remaining factors beyond the study's scope. This underscores the crucial role of marketing strategies in shaping coffee purchasing decisions for coffee shops.

Decision analysis of PPP project's parties based on deep consumer participation.

Although PPP(Public-private partnership) mode has been applied for a long time in infrastructural project, the success rate is not very high. The sustainability of PPP projects is still influenced by many factors. In order to examine the evolutionary stable strategies (ESSs) of social capital, government, and paying consumers, a tripartite evolutionary game model is established in this work. In order to further promote consumer participation, it is necessary to make the assumption that customer oversight and review can have an impact on service prices. The results show: i)The strategy choice of consumer depends on the comparison between supervision cost of consumer and price coefficient for consumer to social capital. ii)Consumer supervision can promote the provision of high-quality services by social capital. iii)The difference between high-quality cost and low-quality cost, subsidy coefficient, price coefficient and supervision cost of consumer are critical factors influencing both evolutionary results and trajectories. This paper also puts forward policy implications for the three stakeholders to promote social capital's high-quality strategy so as to maintain the sustainability of PPP projects.

Helpful clicks: consumers’ perceived diagnosticity of online book reviews

This paper investigates online feedback systems and their perceived diagnosticity in the book industry, using a mixed methods approach, with data retrieved from Amazon. Several variables concur to give the overall perceived diagnosticity of customer reviews: score systems, written text and its themes, and reviews date. Even though reviews are positively biased, long negative reviews are perceived as the most diagnostic. The older the review, the higher the perceived diagnosticity, due to the combined effects of early bird bias and winner circle bias. By understanding the role that variables have on diagnosticity, the findings can be used by scholars, as well as by e-commerce and marketplace webmasters who seek ways to improve the feedback systems of the online platforms in or outside the book industry.

PENGARUH ONLINE CUSTOMER REVIEW, HARGA DAN ONLINE CUSTOMER RATTING TERHADAP KEPUTUSAN PEMBELIAN MELALUI TOKOPEDIA (Studi Pada Konsumen Toko Online Ventela Store Official di Kota Medan)

This study aims to analyze how the influence of online customer reviews, prices and online customer ratting on consumer purchasing decisions Ventela store in Medan city. The influence between online costumer reviews, prices and online costumer ratting will be analyzed partially and simultaneously on employee performance. The form of research used in this research is quantitative research with an associative approach. Sampling was done through non-probability sampling techniques and used 100 respondents as samples. The research findings show that: The results of this study indicate that Online customer review and Online customer review have a significant effect, both partially and simultaneously (together) on consumer purchasing decisions. However, price has no significant effect on consumer purchasing decisions. Thus, the results of this study make an important contribution to the management of Ventela stores in Medan city in improving marketing strategies and employee performance management. Ventela store management can utilize online customer reviews and ratings as one of the factors that can improve consumer purchasing decisions and employee performance.

A Study on Maybelline Products: A Review on Customer Satisfaction

This research aims to conduct a comprehensive study on Maybelline products, a renowned brand in the beauty and cosmetics industry, with a specific focus on understanding customer satisfaction. Maybelline, a subsidiary of L'Oréal, has established itself as a global leader in offering a diverse range of makeup and beauty products. Employing a mixed-methods research design, combining online reviews, surveys, and interviews, this study seeks to explore the perceptions, preferences, and overall satisfaction levels of consumers using Maybelline products. Key objectives include analyzing customer reviews on various platforms, assessing the factors influencing customer satisfaction, identifying popular and well-received products, and understanding customer expectations from the brand. The study also aims to uncover any challenges or areas for improvement as perceived by customers. The findings of this research are expected to contribute valuable insights to Maybelline and the broader beauty industry, aiding in the enhancement of product offerings, marketing strategies, and overall customer satisfaction.

Data Sorting Influence on Short Text Manual Labeling Quality for Hierarchical Classification

The precise categorization of brief texts holds significant importance in various applications within the ever-changing realm of artificial intelligence (AI) and natural language processing (NLP). Short texts are everywhere in the digital world, from social media updates to customer reviews and feedback. Nevertheless, short texts’ limited length and context pose unique challenges for accurate classification. This research article delves into the influence of data sorting methods on the quality of manual labeling in hierarchical classification, with a particular focus on short texts. The study is set against the backdrop of the increasing reliance on manual labeling in AI and NLP, highlighting its significance in the accuracy of hierarchical text classification. Methodologically, the study integrates AI, notably zero-shot learning, with human annotation processes to examine the efficacy of various data-sorting strategies. The results demonstrate how different sorting approaches impact the accuracy and consistency of manual labeling, a critical aspect of creating high-quality datasets for NLP applications. The study’s findings reveal a significant time efficiency improvement in terms of labeling, where ordered manual labeling required 760 min per 1000 samples, compared to 800 min for traditional manual labeling, illustrating the practical benefits of optimized data sorting strategies. Comparatively, ordered manual labeling achieved the highest mean accuracy rates across all hierarchical levels, with figures reaching up to 99% for segments, 95% for families, 92% for classes, and 90% for bricks, underscoring the efficiency of structured data sorting. It offers valuable insights and practical guidelines for improving labeling quality in hierarchical classification tasks, thereby advancing the precision of text analysis in AI-driven research. This abstract encapsulates the article’s background, methods, results, and conclusions, providing a comprehensive yet succinct study overview.

CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviews

Companies with diverse product offerings rely on customer reviews to gauge product reception. Following a purchase, customers often share their opinions on the website. Prospective buyers, prior to deciding, typically peruse these reviews to inform their choices. Analysing such feedback, whether positive or negative, holds paramount importance for companies seeking to improve product quality. Researchers are actively exploring methods to categorize comments based on sentiment scores. Notably, customers may express their reviews in Arabic text. Despite challenges such as the structure and morphology of Arabic text, a scarcity of machine-readable Arabic dictionaries, and limited tools for handling Arabic text, minimal progress has been made in the analysis of Arabic reviews. While some attempts have been undertaken, they have achieved suboptimal accuracy. In response, the authors propose a hybrid deep learning model comprising a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) with GlobalMaxPooling. Through multiple iterations, the authors fine-tuned the proposed model and applied it to the publicly available Arabic Reviews dataset, achieving a notable 95% accuracy, precision, recall, and F1 score. The results indicate that, when compared to alternative models, the proposed model exhibits superior accuracy.

An Improvised Ideology based K-Means Clustering Approach for Classification of Customer Reviews

An Improvised Ideology based K-Means Clustering Approach for Classification of Customer Reviews

The Influence of Entrepreneurial Spirituality and Social Media Adoption on the Sustainability of MSME Performance Mediated by Innovation Capability (Survey on MSMEs in the Tourism Area Sunan Drajat Lamongan)

Technological advancements, computerization, and globalization have made businessescompetitiveacrossallindustries. Micro, small, and medium-sizedenterprises (MSMEs) continue to encounter difficulties with resource scarcity and technology adoption, although accounting for over 80% of employment and contributing to 61.97% of the GDP (gross domestic product). The Sunan Drajat Lamongan Religious Tourism Area is a home to hundreds of MSMEs, ranging in size from apparel and souvenir shops to restaurants. The number of visitors rises dramatically throughout the holiday season before becoming quiet, as is common with tourism in general. Entrepreneurship is a key factor in economic growth and serves as the primary driving force for innovative and long-term growth. By leveraging social media to enhance a company’s competitive advantage throughout the entrepreneurship and operation phases, entrepreneurs who possess an entrepreneurial mindset can aid their organizations in efficiently adapting their organizational framework and processes, thereby mitigating environmental conflicts and tensions within the intricate framework of a dynamic business environment. By using social media, MSMEs may reach their target audience with content and information without having to personally meet them. Social media also offers information in the form of customer reviews of goods, services, and even new ideas for sustainable MSMEs. This study aimed to determine how MSMEs’ use of social media and their ability for innovation can impact their success in Sunan Drajat Lamongan’s religious tourism industry. The data were obtained from 132 small and medium-sized enterprises using questionnaires. Path Least Square (PLS) and descriptive analysis were the methods utilized to analyze the data.
 Keywords: entrepreneurial spirituality, social media adoption, innovation capability, sustainability of MSMEs performance

Impact of Shopee Skincare Price, Reviews, and Quality on Purchasing Decisions

This study investigates the impact of price, online customer reviews, and electronic service quality on skincare purchasing decisions within the Shopee marketplace, focusing on East Java. Through a quantitative approach involving 96 respondents sampled purposively, data was collected via Google Forms and analyzed using descriptive statistics and multiple linear regression in SPSS. Results indicate significant positive effects of these factors on skincare purchasing decisions. Recommendations are made for Shopee and skincare sellers to enhance pricing strategies, prioritize customer reviews, and improve electronic service quality, aiming to optimize consumer decision-making processes and build trust in online transactions. This research contributes insights tailored to the skincare industry within online marketplaces, particularly in East Java, addressing a notable gap in existing literature. Highlight: Shopee skincare purchasing decisions study, East Java, quantitative analysis. 96 purposive sampled respondents enhance study validity and relevance. Findings: price, reviews, service quality impact skincare buying decisions. Keywoard: Shopee, skincare, purchasing decisions, online marketplace, East Java

Ranking products through online opinions: A text analysis and regret theory-based approach

With the development of e-shopping, a list of similar products can be found with a large volume of valuable customer reviews online. However, it is generally difficult to compare various aspects of similar products effectively by understanding all relevant online opinions. To help consumers, in this study, how products are ranked according to online reviews is investigated. Firstly, an SC-LDA (Seed Constraint-Latent Dirichlet Allocation) model, which is an extension of the classical topic model LDA (Latent Dirichlet Allocation), is proposed to extract product features. The must-link and cannot-link seed constraints are invited to estimate the probability expansion/reduction value. They help to affect the topic allocation by additional constraints in Gibbs sampling for a higher accuracy on feature extraction. Secondly, an improved convolutional memory neural network model is devised to analyze the sentiment polarity. It takes the advantages of CNN (convolutional neural network) and Bi-LSTM (bidirectional Long Short-Term Memory) and performs dynamic pooling in CNN to prevent the loss of important features. Besides, the concept of group satisfaction degree is introduced, which makes products be compared according to the Regret Theory. It ranks products without a commonly applied reference point and take consumer psychology into considerations. Finally, in the case study, an illustrative example is presented to evaluate the proposed framework. Categories of experiments show that the proposed framework provides consumers with effective purchase suggestions. Code metadataPermanent link to reproducible Capsule: https://doi.org/10.24433/CO.6445683.v1 and https://doi.org/10.24433/CO.2658577.v1.

Pengaruh Online Customer Review , Online Customer Rating , Diskon Flashsale dan Kemudahan Transaksi terhadap Keputusan Pembelian Pada Marketplace Shopee

This research aims to identify whether there is an influence of online customer reviews, online customer ratings, flash sale discounts, and ease of transaction methods on a consumer's decision to purchase a product on the Shopee market. The type of this research itself is quantitative descriptive with analytical methods. multiple linear analysis using SPSS software. Data collection in this research was c arried out by creating a questionnaire via Google Form. The population of this research is all people in the city of Semarang who have made purchases on the Shopee marketplace, with a sample size of 100 respondents obtained using a purposive sampling technique. After carrying out this research the results obtained were the variables online customer review, online customer rating and ease of transaction. has a positive and significant influence on purchasing decisions on the Shopee marketplace. However, the flashsale discount variable shows that there is no positive influence or in other words it has no effect and is also not significant on purchasing decisions on the Shopee marketplace.

Automatic customer review summarization using deep learning-based hybrid sentiment analysis

Customer review summarization (CRS) offers business owners summarized customer feedback. The functionality of CRS mainly depends on the sentiment analysis (SA) model; hence it needs an efficient SA technique. The aim of this study is to construct an SA model employing deep learning for CRS (SADL-CRS) to present summarized data and assist businesses in understanding the behavior of their customers. The SA model employing deep learning (SADL) and CRS phases make up the proposed automatic SADL-CRS model. The SADL consists of review preprocessing, feature extraction, and sentiment classification. The preprocessing stage removes irrelevant text from the reviews using natural language processing (NLP) methods. The proposed hybrid approach combines review-related features and aspect-related features to efficiently extract the features and create a unique hybrid feature vector (HF) for each review. The classification of input reviews is performed using a deep learning (DL) classifier long short-term memory (LSTM). The CRS phase performs the automatic summarization employing the outcome of SADL. The experimental evaluation of the proposed model is done using diverse research data sets. The SADL-CRS model attains the average recall, precision, and F1-score of 95.53%, 95.76%, and 95.06%, respectively. The review summarization efficiency of the suggested model is improved by 6.12% compared to underlying CRS methods.

A Weighted Stacking Ensemble Model With Sampling for Fake Reviews Detection

Customers use reviews as a primary source of information to judge a product or service. Positive reviews help boost companies’ reputations, increasing their revenue by attracting new clients, and increasing the purchasing order size. On the other hand, negative reviews significantly reduce sales, which might be the case due to competitive advantage. Organizations can use fake (i.e., misleading or fraudulent) reviews to generate fast profits by deceiving customers into buying their products. Recently, various methods to assess the legitimacy of reviews have been introduced using advances in machine learning. However, existing methods fall short of achieving highly accurate detection results for unbalanced classes. We aimed to create a spam review identification model using ensemble-based learning while balancing classes using sampling techniques. This article proposes a weighted stacking ensemble model with sampling (WSEM-S) for efficient fake reviews detection. We used <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$</tex-math> </inline-formula> -gram models to effectively model language data for feature retrieval. The experimental results on three customer reviews datasets: YELPNYC, Deceptive Opinion Spam Corpus (DOSC) v1.4, and Deception datasets show that the proposed model outperforms the conventional machine learning techniques Naïve Bayes, logistic regression, K-nearest neighbor (KNN), random forest, extreme gradient boosting (XGBoost), and convolutional neural network (CNN) as well as the state-of-the-art ensemble models.

Language Abstraction in Negative Online Customer Reviews: The Choice of Corporate Response Strategy and Voice

This study argues that the degree of linguistic abstraction in negative reviews can lead to varying levels of persuasiveness and that tailoring response strategies and voice according to the situation mitigates the impact of negative reviews. This study examines the impact of language abstraction in negative online reviews on potential customers’ attitudes and purchase intention, as well as the moderating effects of managerial responses, response strategies, and response voices on the persuasiveness of negative reviews. The data were collected through three studies that focused on reviews and managerial responses across both the service and functional product categories. The mediation analysis showed that, compared to abstract negative reviews, concrete negative reviews could significantly enhance potential customers’ attribution of responsibility toward service or product providers and their perception of stability and controllability of negative events, leading to a more negative perception of the company, but not lower purchase intention. Additionally, the moderation analysis showed that corporate responses could significantly reduce potential customers’ attribution of responsibility to the disputing company and improve their evaluation. Accommodative responses to concrete negative reviews and defensive responses to abstract negative reviews induced potential customers to make favorable judgments about the firm.

Sentiment analysis with hotel customer reviews using FNet

Recent research has focused on opinion mining from public sentiments using natural language processing (NLP) and machine learning (ML) techniques. Transformer-based models, such as bidirectional encoder representations from transformers (BERT), excel in extracting semantic information but are resourceintensive. Google’s new research, mixing tokens with fourier transform, also known as FNet, replaced BERT’s attention mechanism with a non-parameterized fourier transform, aiming to reduce training time without compromising performance. This study fine-tuned the FNet model with a publicly available Kaggle hotel review dataset and investigated the performance of this dataset in both FNet and BERT architectures along with conventional machine learning models such as long short-term memory (LSTM) and support vector machine (SVM). Results revealed that FNet significantly reduces the training time by almost 20% and memory utilization by nearly 60% compared to BERT. The highest test accuracy observed in this experiment by FNet was 80.27% which is nearly 97.85% of BERT’s performance with identical parameters.

Pengaruh Online Customer Review, Food Influencer dan Content Marketing terhadap Tingkat Kunjungan Bakso Mas Roy Cabang Surabaya Timur

This research aims to determine the influence of online customer reviews, food influencers, and content marketing on the level of customer visits at Bakso Mas Roy East Surabaya Branch. The research was carried out using quantitative methods with an associative approach, the population used was all customers of the East Surabaya branch of Mas Roy meatballs. A sample of 194 respondents who were met by the author at the research location, these results were obtained using the Slovin formula. The research results show that the online customer review variable (X1) is 0.000 &lt; 0.05. t-calculated value -3.812 &lt; t table 1.972 So H1 is accepted, meaning that the online customer review variable has a partially negative effect on the level of customer visits from Bakso Mas Roy. on the food influencer variable (X2) it is 0.001 &lt; 0.05. The calculated t value is 3.320 &gt; t table 1.972. So H2 is accepted, meaning that the food influencer variable partially influences the level of visits. content marketing variable (X3) is 0.000 &lt; 0.05. The calculated t value is 3.947 &gt; t table 1.972. So H0 is rejected and H3 is accepted, meaning that the content marketing variable partially influences the level of visits.

The Effects Of Social Media Content, Influencer Marketing And Customer Reviews On Purchasing Decisions

This research aims to determine the effect of social media content, influencer marketing , and customer reviews on purchasing decisions on Shopee online marketing platform during period January-March 2024. The independent variables in this research are social media content, influencer marketing , and customer reviews , while the dependent variable is purchasing decisions. This research uses primary data in the form of questionnaire results from respondents. This research uses a purposive sampling technique . The method used is a type of quantitative research . The analysis used in this research is multiple linear analysis. In this research, it shows that social media content has significance effect on purchasing decisions, influencer marketing has no effect on purchasing decisions, customer reviews has no effect on purchasing decisions but the variables social media content (X1), influencer marketing (X2) and customer reviews (X3) simultaneous influence on purchasing decisions (Y) with a significance value (Sig) of 0.000 &lt; 0.05.

The Influence of Hedonic Shopping Motivation, Ease of Use, Customer Reviews, and Electronic Word of Mouth on Impulse Buying Behavior at Shopee E-Commerce During The COVID-19 Pandemic

This study aims to determine, analyze, and explain the effect of hedonic shopping motivation, ease of use, customer reviews, and electronic word of mouth on impulse buying behavior at E-commerce Shopee during the COVID-19 pandemic. The approach used in this research is descriptive method and quantitative approach. The data analysis method in this study uses Partial Least Square (PLS) and data collection in this study uses a survey method, with the research instrument used is a questionnaire. The population in this study are people who shop using Shopee, the number of which is not known with certainty. The sample used in this study was 211 respondents, with the sampling technique using purposive sampling. The results of this study indicate that hedonic shopping motivation has a positive and significant effect on impulse buying behavior; customer reviews have a positive and significant effect on impulse buying behavior; electronic word of mouth has a positive and significant effect on impulse buying behavior; ease of use has no effect on impulse buying behavior.

Positive or Negative Sentence Feedback Identifier

Abstract: The "Positive or Negative Sentence Feedback Identifier Project" is a natural language processing (NLP) initiative designed to automatically classify and analyse sentences or text- based feedback as either positive or negative. This project aims to streamline sentiment analysis and opinion categorization by employing machine learning and NLP techniques. Its potential applications include sentiment analysis in customer reviews, social media monitoring, and opinion mining, ultimately providing valuable insights to businesses and individuals. It's crucial to gauge the overall sentiment and tone of the feedback. Positive feedback typically conveys satisfaction, using enthusiastic language and specific compliments about at's working well. In contrast, negative feedback often carries a critical tone, highlighting issues or areas of concern with the project. Pay attention to emotional indicators, the specificity of comments, and whether the feedback offers constructive suggestions for improvement. Evaluating feedback within the context of the project's goals and objectives is essential to understanding its impact and guiding necessary actions for project enhancement. Enhance security with two-factor authentication and encryption, while implementing user authentication and authorization controls. Integrate third-party services for expanded functionality and ensure mobile responsiveness for an improved user experience. Explore AI for automation and data analysis, offer robust analytics, and gather user feedback. Prioritise accessibility, optimise performance, and gamify the project with badges and leaderboards. Enable offline functionality, foster community engagement, and align features with userneeds and scalability goals. The project's development encompasses a comprehensive range of solutions, including the implementation of a sophisticated sentiment analysis model, efficient data collection and preprocessing methods, and the incorporation of scalable real-time processingarchitecture. Furthermore, the project's innovative facets encompass a dynamic blend of emotion analysis, contextual analysis, and predictive sentiment analysis, which significantlyaugment its adaptability and effectiveness across diverse domains and use cases.