Customer Comments Research Articles

Aspect-Based Sentiment Analysis for Online Products

A number of resources are now available for gauging public opinion about businesses, products, services, brands, and events because of the advent of e-commerce. Customers may find it difficult to distinguish between legitimate assessments and biased or false reviews, which leads to worse goods or services. Aspect-based sentiment analysis is utilized in this study to develop a natural language processing model to examine customer reviews and comments to ascertain the sentiment expressed towards certain qualities or components of a good or service. A few procedures involved in this undertaking include aspect extraction, sentiment classification, training, feature extraction, and dataset preparation. The T5 model will be used to train the model using a dataset of customer reviews, and it will be evaluated using a variety of performance measures, including accuracy (84.62%), precision (84.58%), recall (84.62%), and F1-score (83.39%). The project's findings will help customers locate services that meet their needs, and they will also assist businesses in learning more about the advantages and disadvantages of their goods and services.

Development of an Artificial Intelligence Based Correction System for Spelling Errors in Product Reviews

E-commerce has experienced rapid growth in recent years and continues to expand dynamically. In this sector, maximizing customer satisfaction and enhancing the shopping experience are recognized as important strategic initiatives. To maximize customer satisfaction, it is essential to accurately determine customer needs and provide appropriate solutions to meet demand. In this context, feedback obtained from customers holds significant importance. However, customer comments often contain spelling errors, complicating the analysis of these comments. This study aims to automatically correct spelling errors in user comments regarding products sold on the e-commerce site Trendyol.com. For this purpose, a system based on transformer architecture has been created. Various spelling error detection and correction models were subsequently developed based on this architecture. Prediction models have been developed using two separate datasets consisting of Trendyol user comments and two additional datasets, including the Turkish Spelling Check Dataset taken from the Hunspell library, and the effects of these four datasets on prediction performance have been examined. The success of the models has been evaluated using the Accuracy metric. The performance of the developed models was also compared with that of the model in the Zemberek library. As a result of the study, it has been observed that the utilization of the Turkish Spelling Check Dataset positively influences prediction performance. The developed system enhanced customer experience by correcting spelling errors in comments.

Brand Reputation and Trust: The Impact on Customer Satisfaction and Loyalty for the Hewlett-Packard Brand

Reputation is shaped depending on factors such as the quality of products and services offered by a brand to its stakeholders, its reliability, and its innovative aspect in the eyes of stakeholders. The sustainability of a brand reputation depends on the brand creating a positive perception by fulfilling its social responsibilities and maintaining this perception in the long term. In this study, the brand reputation of Hewlett-Packard (HP) computers is evaluated through customer reviews. The data set in the study consists of 2012 customer reviews obtained from Hepsiburada, one of the most widely used e-commerce platforms in Turkey. Sentiment analysis and text mining artificial intelligence methods were used in the study. For sentiment analysis, the Naive Bayes method, which is one of the machine learning methods, was used, and the comments were divided into three groups as positive, negative, and neutral. In the study, 82% of the customer comments were positive, 11% were negative, and 7% were neutral. The fact that most of the comments consist of positive sentiments shows that HP Computer has a positive reputation in the eyes of stakeholders consisting of customers. Comments consisting of negative and neutral emotions show the aspects that the brand needs to improve. In the study, the text mining method emphasises the prominent features of the brand in the comments. This study makes an important contribution to the reputation assessment of brands and to ensuring sustainable brand reputation.

Sentiment Analysis of Joglo Wifi UMKM Service with Naive Bayes Method

In today's digital era, many businesses face challenges in managing and responding to customer feedback and suggestions contained in comments. Joglo Wifi Corner UMKM Business Center & Coffee experiences similar difficulties, where the lack of customer feedback management negatively impacts service quality and customer satisfaction. In this study, we aim to develop and implement a sentiment analysis system that is able to classify customer sentiment into positive, negative, or neutral. The process begins with data collection. customer comments from the official Joglo Wifi Corner website, which are then processed through a preprocessing stage including tokenization, stop word removal, and lemmatization. Then, a Logistic Regression Naive Bayes model is drilled using the processed data to classify sentiment. The evaluation results show that this system achieves an accuracy of 91.67%, with an average precision of 0.646, an average recall of 0.805, and an average F1-Score of 0.701. The implementation of this system provides valuable insights for Joglo Wifi Corner managers in making strategic decisions to improve service quality. By responding more effectively to customer feedback, Joglo Wifi Corner promises that this research can improve customer satisfaction and expand the company's market coverage and identify areas for improvement based on customer feedback, thereby strengthening customer relationships. This approach also uses Agile Development system development methodology to ensure iterative and responsive development to changing user needs.

Sustainable Brand Reputation: Evaluation of iPhone Customer Reviews with Machine Learning and Sentiment Analysis

Brand reputation directly influences customer trust and decision-making. A good reputation can lead to greater customer loyalty, commitment, and advocacy. This study aims to understand the effects of brand reputation on customer trust and loyalty and to determine how brands can protect their reputation. This study, which was conducted on the iPhone 11 sample by obtaining statistical data from customer reviews, can be adapted and used by researchers and companies that want to measure brand reputation. In this study, customer reviews for the iPhone 11 phone on the Trendyol e-commerce site, the largest e-commerce platform in Turkey, are analyzed using sentiment analysis and machine learning methods. While 85 percent of customers are satisfied with the iPhone 11, 13 percent are dissatisfied with it. The neutral comment rate of 2 percent indicates that some customers do not express a clear positive or negative opinion about the product. In the comments of customers who bought the iPhone 11, there are those who express satisfaction with the quality, technical features, performance, and price/performance ratio of the product, as well as those who express significant complaints about delivery, quality, price, and customer service. Neutral comments generally focus on the product itself, price, quality, shipping, and packaging, and make informative evaluations. A sustainable reputation is based on the extent to which an organization embraces ethical principles, social responsibility, and sustainable practices throughout its operations and business relationships. Brands can improve, protect, and increase their brand reputation by considering and analyzing the thoughts and feelings of their customers. For this, they should develop policies and strategies to reinforce their strong features and improve their faulty and deficient features.

Analysis of machine learning approaches to determine online shopping ratings using naïve bayes and svm

This research aims to identify and compare the effectiveness of Naïve Bayes and Support Vector Machine (SVM) algorithms in classifying ratings based on customer comments on the Lazada online shopping platform. The main issues identified include data uncertainty, model selection and optimization, as well as improving efficiency and scalability. Using a dataset of comments and reviews from Lazada, this study conducts an analysis using both algorithms to determine which is most effective in classifying comments into appropriate ratings. The research methodology includes data collection, text preprocessing, algorithm implementation, and evaluation using a confusion matrix to measure accuracy, precision, recall, and F-measure. This analysis is supported by data visualization using Python, allowing for in-depth interpretation and understanding of the results. The research findings show significant differences in the performance of both algorithms, with each having strengths in certain aspects of classification. The discussion in this study interprets these results to address the research questions formulated and demonstrates the practical application of machine learning theory in real-world data processing. This study concludes that both algorithms have significant potential in sentiment classification but require further adjustment and optimization to improve accuracy and efficiency. Recommendations for further research include the development of hybrid models or new approaches that can address the identified limitations, as well as exploration of more diverse datasets to test the scalability of the proposed solutions.

Schadenfreude and Sympathy: Observer Reactions to Malicious Joy During Social Media Service Recovery

Complex social dynamics occur when complaints are voiced on firms’ social media channels. In combination, a complainer criticizes a firm, which may be responded to uncivilly by different online personas (i.e., internet trolls or loyal customers), with virtually present observers watching how a firm responds. This research examines customer-to-customer (C2C) uncivil commentary from troll and loyal customer personas perceived by observers to elicit schadenfreude (malicious joy due to another's adverse event). Three studies show how C2C schadenfreude targeting a complainer elicits sympathy from observers, which influences observers’ future purchase intent. Study 1's online content analysis using field data shows the frequency of C2C schadenfreude during social media service recovery. Study 2 uncovers moderated mediation of C2C schadenfreude–sympathy–purchase intent, with loyal customer persona comments producing more observer sympathy than troll persona comments. Study 3 finds the harmful effect of observer sympathy on purchase intent varies based on how or if a firm addresses the C2C dialogue. This research uses a novel cognition (perceived schadenfreude from another's comment), examines a lesser-studied emotion in marketing (sympathy), and is the first marketing-related work to incorporate backlash theory from organizational management to exemplify how loyal customer comments produce a backlash effect in observers.

Outdoor hospitality performance: Through the lens of the balanced scorecard and its customer perspective

The purpose of this study is to lay the foundations for measuring customer performance in the outdoor hospitality sector and encourage relevant internal benchmarking through an adapted balanced scorecard. The literature on balanced scorecard and customer performance is classified by identifying their antecedents in the context of outdoor hospitality management. Using an inductive approach, the study employs a lexicometric analysis to identify the main categories of customer satisfaction in a well-known European camping chain. In addition, this research proposes a methodological building block adapted for camping business that integrates multiple classes and attributes into the customer perspective of the BSC model addressing the current over-simplification of this element of the model. This study highlights the importance of integrating customer feedback into a performance measurement system and provides a practical tool for managers to apply and adapt customer comments into a campsite BSC system.

Sensing hotel customers distribution and their sentiment variations using online travel agent data: a case of Shanghai star-rated hotels

ABSTRACT Customer numbers and comments have been extensively studied to increase hotel arrivals and loyalty, whereas the specific distribution and sentiment variations have received less attention. This study constructed a data set of hotel customers and the deep learning model was applied to quantify unstructured text, which can mine the distribution and sentiment variation patterns of different star hotel customers. The findings show that customers of different star-rated hotels have different variation patterns of sentiment and distribution. There is a negative correlation between the visit heat and sentiment of some high-star hotels in various administrative regions: regions with lower visit heat have higher sentiment scores. In addition, season and location are important factors that affect customers’ sentiments. This study is the first to use a quantitative approach to examine the distribution and sentiment variation patterns of hotel customers. It provides insights into appropriate marketing strategies for the hotel industry and offers practical suggestions to hotel customers.

Computer security technology in E-commerce platform business model construction

The global e-commerce market is expanding rapidly as the big data era advances and the e-commerce industry thrives. This paper aims to discuss the application of computer security technology in constructing an e-commerce platform business model. The research aims to find effective security technology solutions to strengthen the security of e-commerce platforms, protect user information and rights, and enhance the sustainable development of business models. Big Data-assisted E-Commerce Business Model (BD-ECBM) construction is discussed to overcome the e-commerce platform issues and positively impact marketing strategy decision-makers by raising their level of awareness. The business decision-making process is a series of steps that help businesses overcome obstacles by collecting relevant data, analyzing all relevant alternatives, and settling on a course of action. Big data analytics can improve business management with data fusion technology in many ways. The system's framework of the information service layer, the application-level layer, and the client session layer was developed using the Business model paradigm for accounting for e-past, commerce's capabilities of the platform, and an analysis of supply and demand. It can monitor its rivals in near real-time, adjusting prices, offering more attractive deals, and analyzing negative customer comments to see if it can outperform its rivals. The trial results demonstrate the effectiveness of this method of making marketing decisions and formulating a strategy. Hence, the BD-ECBM technique improves customers' overall satisfaction and experience with the brand while raising the latter's profile.

The Impact of Social Media on Consumer Behaviour

Thanks to technology, consumers can research things, label them, offer criticism in equal proportion, and do much more. As a result, a lot of businesses these days have social media pages to supplement the data they have about their products. These pages contain customer comments about their items, and people are more likely to relate to a business after reading multiple evaluations. Because the paper deals with how social media affects consumer behavior, it is a quantitative study. 116 respondents made up the sample, and the statistical analysis led to results about both univariate and bivariate analysis. Once the study factors have been analyzed, we can create a social network-based customer profile.Similarly, it is possible to observe the degree of effect and the true impact of social media on behavior changes following the completion of a sophisticated statistical analysis utilizing SPSS and the analysis provided by the web platform that hosted the questionnaire.

Brand Trolling Engagement Behavior (BTEB) of Customers: A Challenge for Customer-Brand Relationship

The extensive use of social media has resulted in higher customer engagement, and firms use these platforms to communicate with customers, share information about brands and improve brand popularity. Social media provides the same platform for customers to share their views about firms and brands. Online communities or groups on social media facilitate interactions and information sharing among members. When the group members start using these social media platforms to post negative views, it is termed trolling. Customer comments on social media are crucial in shaping a firm’s reputation; therefore, when a brand falls short of customer expectations, they might feel cheated and betrayed and indulge in brand trolling activities termed Brand Trolling Engagement Behavior (BTEB). Customer comments on social media are crucial in shaping a firm’s reputation and significantly impact the brand. Trolling is an emerging research topic, and empirical studies on brand trolling are relatively scarce. This paper attempts to develop and validate a scale to measure customers’ BTEB and, subsequently, the impact of trolling on a brand. The data for the study was gathered from respondents in stages. Two factors, agitation and dissatisfaction, were obtained in the results, which explain the reasons why customers troll a brand on social media. Significant results were obtained where customers feel that brand trolling is a challenge for the firms and it affects the popularity and image of the brand. The research provides insights about the BTEB of customers on social media and would help the firms to manage customer-brand relationships.

Logistics customer service management on the example of a manufacturing company

Purpose: The aim of the article is to analyze the operation of company X in the context of logistic customer service in practice. Design/methodology/approach: The idea of the work is to present the theoretical part of customer service and compare it to logistic customer service in practice. It also includes comparisons of practical solutions of company X to theoretical requirements. Findings: The research issue discussed in the article was a survey. Its purpose is to present customer service in Patrick's Day in company X. 81 people of different genders and age groups responded anonymously to the survey questions 15- >60 years. General knowledge of the logistics industry and responses from opinion makers were taken into account. The responses of the surveyed people were presented graphically along with their descriptions. Research limitations/implications: The practical part is intended to reflect the actual compliance of company X with the imposed rules. The Logistics Customer Service Principles were created to ensure a consistent and effective approach to customer service in the context of logistics. Practical implications: The type of customer service strategy depends on the specific goals and needs of a given business. The essence of logistic customer service is the effective management of the flow of products and services from the place of production to the place of consumption in order to meet customer needs. Logistics customer service covers many aspects, such as planning, controlling and monitoring the flow of goods, inventory management, transport, warehousing and coordination of activities between various links in the supply chain. Social implications: Customer service also means the ability to accept customer opinions and comments with an open mind. Customers should be able to express their opinions and complaints and then respond effectively. Originality/value: The article draws attention to the importance of a non-routine approach to the dynamics of opportunities. This is important for management as a scientific discipline, but also for managers, which indicates various possible development paths. Keywords: Customer, logistic customer service, logistics. Category of the paper: Research paper.

Leadership development through 360-degree multi-rater feedback—An experience sharing of need, approach, roll-out, and the impact

The organizational development (OD) interventions carried out by the assessment center identifying the competencies becomes effective only if the expectation of the stakeholders is met. A 360-degree multipurpose intervention is to assess and develop project director’s leadership capabilities and enable them to execute Mega Infrastructure Projects in India executed by Larsen and Toubro, the leading engineering, procurement and construction (EPC) players of India. Implementing such Mega Projects by maintaining time, cost, safety, and quality parameters require leadership skills of high order. To meet out this requirement implementation partner interacted with few project directors from each business verticals such as nuclear, hydel, metro, defense, special bridges and ports and harbor, to understand the role holders’ challenges and the expectations. L&T Heavy Civil Infrastructure (HCI) Leadership Competency framework was thus drafted looking into the role intensity and specific role-based challenges of the Mega Project Leaders. The questionnaires were designed to cover all dimensions and sub dimensions of 8 competencies, covering 40 behavioral Indicators. the questionnaires were hosted on the online platform to including self, supervisor, direct repartees, peers, customers, and other stakeholders. Validation to the assessment of each dimension and sub-dimensions as qualitative feedback is done with simple average scores and the range. The study found that execution leadership was the highest rated competency followed by customer engagement and talent management. The study also found that strategic orientation and decision making were rated low compared to other competencies, got validated by comments of customers as well. This is quite evident from the feedback that was taken after 9 months of the intervention. The study by using Delphi technique revealed that by providing feedback from all stakeholders supported by systematic coaching, 88% participants showed improvement in the low rated items. The study further proved that with proper feedback and coaching at an individual level with required trust and keeping development as the core agenda and without linking to any other HR processes like appraisal and promotion, majority of the participants took full ownership, interest and worked on their individual competency development showing their learning agility.

Combination of streamers' product description and viewers' comments: moderating effect of streamer–viewer relationship strength

PurposeThis study examines the relationship between streamers' product descriptions, customer comments and online sales and focuses on the moderating effect of streamer–viewer relationship strength.Design/methodology/approachBetween June 2021 and April 2022, the structured data of 965 livestreaming and unstructured text data of 42,956,147 characters from two major live-streaming platforms were collected for the study. Text analysis and regression analysis methods were employed for data analysis.FindingsFirst, the authors' analysis reveals an inverted U-shaped relationship between comment length and product sales. Notably, comment volume and comment emotion positively influence product sales. Furthermore, the semantic richness, emotion and readability of streamers' product descriptions also positively influence product sales. Secondly, the authors find that the strength of streamer–viewer relationship weakens the positive effects of comment volume and comment emotion without moderating the inverted U-shaped effect of comment length. Lastly, the strength of streamer–viewer relationship also diminishes the positive effects of emotion, semantics and readability of streamers' product descriptions on product sales.Originality/valueThis study is the first to concurrently examine the direct and interactive effects of user-generated content (UGC) and marketer-generated content (MGC) on consumer purchase behaviors in livestreaming e-commerce, offering a novel perspective on individual decision-making and cue utilization in the social retail context.

Intelligent performance evaluation of e-commerce express services using machine learning: A case study with quantitative analysis

Amidst the robust development of the service economy and information technology, the information age has significantly transformed consumption concepts and service demands. The requirements for logistics services from customers have become increasingly stringent. Beyond price and speed, quality has steadily emerged as the most crucial factor. When evaluating express services, experts primarily choose indicators from an enterprise perspective, mainly overlooking customer perception. The purpose of this paper is to establish a key index system for assessing the quality of express services aimed at improving the service quality of express deliveries within the development mode of intelligent logistics. In terms of methodology, we proposed a quantitative and qualitative e-commerce logistics service evaluation system. Specifically, we developed a key index system for assessing the quality of express services based on the theory of the six senses and the selection from an index library at first. And then, we ascertained the weight of each index in the evaluation by analyzing the proportion of customer comments. We employed analysis methods of machine learning, text data processing, mathematical statistics, and big data technology to determine the evaluation index and evaluation model of express service. Finally, our primary findings from the empirical verification and analysis of a real express enterprise indicate that this evaluation model can effectively assess the quality of express services. Our model can evaluate the current service quality and predict the quality of future services. We have derived some interpretations and conclusions based on these analyses and findings. Firstly, the level of customer perception is of great importance in the evaluation of express service quality. Secondly, our model can provide valuable feedback for express enterprises to improve their services. Lastly, we proposed corresponding improvement strategies to enhance the service quality of express enterprises under the intelligent logistics development mode.

Using customer feedback to prioritise remediation return on investment and improve customer experience

With the myriad of customer comments available on digital media, it is paramount for organisations to identify the breadth of compliments and complaints that customers are discussing, to analyse and understand drivers of customer sentiment and to know where to prioritise available resources such that the resolution of issues produces the biggest rewards for customers — and the business. Many organisations already successfully identify the issues that customers report (and there may be dozens of them). Often, they select the issues with the highest volume (impacting the most customers) and focus on resolving those first. Additionally, they may target the issues that have the highest negative sentiment. While both approaches are useful, they usually lack the ability to track newly developing issues/trends and, most importantly, are unable to accurately prioritise where to start (in the case of issues with similar volumes) and how to quantify the return on investment (ROI) associated with the remediation of each issue. This paper focuses on the technical capabilities needed to be able to identify the drivers of customer conversations and sentiment, the approaches needed to quantify both the importance of taking action from the customer's standpoint and the impact for the business in doing so, allowing a measured approach to improved customer experience. Analysing, prioritising and resolving cross-channel issues creates happier customers, higher rates of acquisition, increased repeat business and, ultimately, improves the bottom line.

Research on the weak demand signal identification model of innovative product based on domain ontology construction

PurposeThis paper investigates the semantic association mechanisms of weak demand signals that facilitate innovative product development in terms of conceptual and temporal precedence, despite their inherent ambiguity and uncertainty.Design/methodology/approachTo address this challenge, a domain ontology approach is proposed to construct a customer demand scenario-based framework that eliminates the blind spots in weak demand signal identification. The framework provides a basis for identifying such signals and introduces evaluation indices, such as depth, novelty and association, which are integrated to propose a three-dimensional weak signal recognition model based on domain ontology that outperforms existing research.FindingsEmpirical analysis is carried out based on customer comments of new energy vehicles on car platform such as “Auto Home” and “Bitauto”. Results demonstrate that in terms of recognition quantity, the three-dimensional weak demand signal recognition model, based on domain ontology, can accurately identify six demand weak signals. Conversely, the keyword analysis method exhibits a recognition quantity of four weak signals; in terms of recognition quality, the three-dimensional weak demand signal recognition model based on domain ontology can exclude non-demand signals such as “charging technology”, while keyword analysis methods cannot. Overall, the model proposed in this paper has higher sensitivity.Originality/valueThis paper proposes a novel method for identifying weak demand signals that considers the frequency of the signal's novelty, depth and relevance to the target demand. To verify its effectiveness, customer review data for new energy vehicles is used. The results provide a theoretical reference for formulating government policies and identifying weak demand signals for businesses.

The Untested Assumption: Can a Net Promoter Study Be Used to Improve Net Promoter Score?

Despite scholarly critiques, use of the Net Promoter Score (NPS®) continues to grow in popularity among firms. Even researchers who criticize NPS recognize its potential for predicting desirable customer behaviors and revenue growth. However, a firm’s goal in measuring NPS is not to simply assess it, but to be empowered to improve that score. This goal begs an important question: Does a “net promoter” study provide the insights that a firm needs to improve their NPS? The critical, but untested, assumption in NPS use is that the insights gained from open-ended customer comments in a net promoter study can be used to set improvement priorities that will increase future NPS likely-to-recommend ratings. Through two distinct studies, one in a business-to-business context with auto dealership decision-makers and one in a business-to-consumer context with vehicle repair customers, we investigate this assumption. Our results reveal that the critical untested assumption of a net promoter study is questionable. The convergence is low to moderate between open-ended priorities from a net promoter study and predictors of the standard ‘likely-to-recommend’ NPS question. We also find that the convergence between customers’ open-ended priorities and their stated and derived priorities from closed-ended responses is higher for NPS detractors and passives than promoters, but it is still only moderate. The strength of this convergence of priorities is also impacted by the wording of the questions used to elicit customers’ open-ended priorities. Firms using open-ended comments to set priorities should ask customers, especially detractors, to identify areas for improvement. In addition, they should supplement open-ended customer feedback with closed-ended questions to get customers’ performance ratings in relation to their specific needs.

The role of digital communication and display in interior design processes

In light of the intellectual and technological progress within the current developments of time, as well as the emergence of digital tools and means of display and communication, which had a major role in the shifts of the time of globalization in various commercial and economic fields, as well as areas of transferring the design image and its stages of development to customers and the convergence of views between the customer and the interior designer, which are the most important pillars of the design process As a whole, and accordingly, there is an urgent need for a process of intellectual balance between them through digital tools from the technical side and through social media from the intellectual side. Customer comments via social media, which facilitates the process of generating feedback for designers. The problem is embodied in the following question: "How can digital modeling tools and social media be employed in the field of interior design to obtain a contemporary design process?" And then its objectives, limits, and definition of its terminology, as the research sample was represented by the engineering offices registered with the Iraqi Engineers Association, and after reviewing previous studies and building the theoretical framework, the research dealt with two axes, the first (the concept of the design process and its variables’ connection with the variables of the era and technology), and the second (the role of the customers’ position in the process After building the theoretical framework and reaching a set of indicators, a questionnaire was built to be analyzed in the light of it, and after ensuring the validity and reliability of the tool, a random sample was selected from the number of answers obtained from the research community, and the statistical analysis method was used For the questionnaire, a set of statistical results were reached in order to influence a set of conclusions that can be generalized to the research community, and then a set of recommendations and research proposals.