ABSTRACT
After release of Web 2.0 in 2004 user spawned contents on the internet eminently in abundant review sites, online forums, online blogs, and many other sites. Entire user generated contents are considerable bunches of unorganized text written in different languages that encompass user emotions about one or more entities. Mainly predictive analysis exerts the existing data to forecast future outcomes. Currently, a massive amount of researches are being engrossed in the area of opinion mining, also called sentiment analysis, opinion extraction, review analysis, subjective analysis, emotion analysis, and mood extraction. It can be an utmost choice whilst perceiving the meaning and patterns in prevailing data. Most of the time, there are various algorithms available to work with polling. There are contradictory opinions among researchers regarding the effectiveness of algorithms. We have compared different opinion mining algorithms and presented the findings in this paper.
ABSTRACT
PurposeA huge volume of published research articles is available on social media which evolves because of the rapid scientific advances and this paper aims to investigate the research structure of social media.Design/methodology/approachThis study employs an integrated topic modeling and text mining-based approach on 30381 Scopus index titles, abstracts, and keywords published between 2006 and 2021. It combines analytical analysis of top-cited reviews with topic modeling as means of semantic validation. The output sequences of the dynamic model are further analyzed using the statistical techniques that facilitate the extraction of topic clusters, communities, and potential inter-topic research directions.FindingsThis paper brings into vision the research structure of social media in terms of topics, temporal topic evolutions, topic trends, emerging, fading, and consistent topics of this domain. It also traces various shifts in topic themes. The hot research topics are the application of the machine or deep learning towards social media in general, alcohol consumption in different regions and its impact, Social engagement and media platforms. Moreover, the consistent topics in both models include food management in disaster, health study of diverse age groups, and emerging topics include drug violence, analysis of social media news for misinformation, and problems of Internet addiction.Originality/valueThis study extends the existing topic modeling-based studies that analyze the social media literature from a specific disciplinary viewpoint. It focuses on semantic validations of topic-modeling output and correlations among the topics and also provides a two-stage cluster analysis of the topics.
ABSTRACT
In this contemporary era of digital marketing, ecommerce has emerged as one of the most preferred methods for day-to-day shopping. Ever since the COVID-19 pandemic, online shopping behavior has forever changed to less or no human-to-human interaction. As a result, it is getting more difficult for e-commerce enterprises to observe and evaluate market trends, particularly when done through consumer behavior analysis. To identify behavioral patterns and customer review-rating discrepancies, extensive analysis of product reviews is a substantial research field. Lack of benchmark corpora and language processing techniques, predicting review ratings in Bengali has become increasingly problematic. This paper thoroughly analyzes the approach to product review rating prediction for Bengali text reviews exploiting our own constructed dataset that was collected from an e-commerce website called DarazBD1. We acquired product reviews with labels known as ratings of five sentiment classes, from "1"to "5". It is noteworthy that we established a well-balanced dataset using our automated scraping system and a significant amount of time and effort is spent to maintain quality standards through the human annotation process. Exploration of multiple approaches to machine learning models such as logistic regression, random forest, multinomial naïve Bayes, and support vector machine, the best classification accuracy score of 78.63% is achieved by SVM. Subsequently, using Word2Vec, FastText, and GloVe embeddings with three deep neural network(DNN) architectures: CNN, Bi-LSTM, and a combination of CNN and Bi-LSTM, CNN+Bi-LSTM gave the highest accuracy score of 75.25% among the DNN architectures. © 2022 IEEE.
ABSTRACT
Online consumer reviews play a pivotal role in boosting online shopping. After Covid-19, the e-commerce industry has been grown exponentially. The e-commerce industry is greatly impacted by the online customer reviews, and a lot of work has been done in this regard to identify the usefulness of reviews for purchasing online products. In this proposed work, predicting helpfulness is taken as binary classification problem to identify the helpfulness of a review in context to structural, sentimental, and voting feature sets. In this study, the authors implemented various leading ML algorithms such as KNN, LR, GNB, LDA and CNN. In comparison to these algorithms and other existing state of art methods, CNN yielded better classification results, achieving highest accuracy of 95.27%. Besides, the performance of these models was also assessed in terms of precision, recall, F1 score, etc. The results shown in this paper demonstrate that proposed model will help the producers or service providers to improve and grow their business.
ABSTRACT
Due to the Coronavirus (Covid-19) pandemic, there was a positive shift in online shopping. On an e-commerce website like Shopee, consumers may post comments under the products they have purchased. This research study aims to conduct sentiment analysis on product reviews as customer recommendations in Shopee Philippines. The product reviews were first scraped from Shopee. After which, it is preprocessed and then annotated using VADER. The customers' sentiments were analyzed using Multinomial Naive Bayes (MNB) and Support Vector Machine (SVM). The confusion matrix and a classification report were then used to determine the accuracy value, the precision value, the recall value, and the F-measure value of the results from the models. Lastly, the results from a survey would justify the model's results to customer recommendations. The final results of the research study show how reviews with positive, negative, and neutral sentiments can affect a product's condition to be recommended to other consumers or not. Based on the analysis of the product reviews, 83.6% are positive, 9.1% are negative, and 7.3% are neutral. The SVM model is found to be a better model than MNB which got an 83% accuracy score. The survey results which validated the model's results have found that 75.8% of the respondents would recommend a store or a product based on the number of positive reviews. © 2022 IEEE.
ABSTRACT
The popularity of social media for business and marketing is on a definite rise. Although researchers are increasingly studying various aspects of SNS (social networking sites) marketing and e-commerce, there are still few studies into the impact of Instagram due to the relatively new nature of the application. Therefore, the main objective of this study is to provide an analysis of the statistical significance of Instagram likes on consumer attitude and purchase intention on a linked e-commerce site. The secondary objective is to compare demographic data based on age, gender, and educational categories of the respondents. The final aim is to bridge the gap in literature and provide practical implications which would be useful to professionals in brand and marketing management. Based on a systematic literature review, first order structural equation model was proposed and tested. The empirical data was derived from a survey of 166 subjects in Bosnia and Herzegovina. Upon the collection of data, factor analysis was conducted in SPSS to ensure the validity and reliability through items' loadings and Cronbach's Alpha values. Furthermore, the empirical hypothesis testing was conducted in SmartPLS 3 in order to investigate direct effects of variables in the model. The results indicated that there is a significant statistical impact of Instagram likes on consumer attitude and purchase intention. Currently, due to the relatively recent use of the app for business and marketing purposes, there is a very limited amount of research on consumers' involvement and attitude on Instagram and its impact on the likelihood of purchase. Therefore, one can consider the theoretical and practical implications of this study to be evident.
ABSTRACT
Purpose>The expanded use of mobile devices for shopping has made mobile showrooming a frequent practice among omnichannel shoppers. This paper aims to shed light on the role of mobile dependency and uncertainty reduction strategies together with the motivation of getting the best value for money in showrooming behaviours and user-generated content (UGC) creation.Design/methodology/approach>Data were collected by means of a questionnaire answered by 659 shoppers in two product categories: clothing and consumer electronics. The research model was tested through partial least squares.Findings>The results suggest that mobile showrooming attitude is positively affected by mobile dependency, value consciousness and need for touch, and negatively by perceived risk of mobile shopping. The results also reveal how UGC is created by showroomers and suggest this behaviour is linked to mobile dependency in the clothing category.Research limitations/implications>All the individuals in the sample had some experience in showrooming, which could affect the results regarding showrooming attitude and intentions. Future research should consider the role of experience and also validate the results across a larger number of product categories.Practical implications>Mobile showrooming is a challenge for multichannel retailers. This paper reveals certain ways in which multichannel retailers could deal with showroomers as potential customers.Originality/value>This study is the first to analyse the role of mobile dependency in showrooming and the chain of effects towards mobile showrooming attitude, behaviour and UGC creation in two different product categories.
ABSTRACT
Online marketing and e-commerce firms were already prospering in Bangladesh during this era of internet technology. Because people are under lockdown due to the COVID-19 epidemic, internet shopping has become the major platform for purchasing because it is the safest option. It sped up the time it took for firms to go online. More online product service providers improve people's lives, but it also raises concerns about product quality and service. As a result, it is simple for new clients to dupe while purchasing online. Our objective is to create a system that uses Natural Language Processing to assess client feedback from online purchasing and deliver a ratio of good and bad comments written in Bangla from past customers (NLP). We gathered approximately 6000 comments and views on the product to conduct the study. As classification approaches, we used sentiment analysis, as well as KNN, Decision Tree, Support Vector Machine (SVM), Random Forest, and Logistic Regression. With an accuracy of 94.78 percent, SVM outperformed all other methods. © 2022 IEEE.
ABSTRACT
Purpose>Consumer adoption of online shopping continues to increase each year. At the same time, online retailers face intense competition and few are profitable. This suggests that businesses and researchers still have much to learn regarding key antecedents of online shopping adoption and success. Based on extensive past research that has focused on the importance of various online shopping antecedents, this work seeks to provide an integrative, comprehensive nomological network.Design/methodology/approach>The authors employ a mixed-methods approach to develop a comprehensive model of consumers online shopping behavior. To that end, in addition to a literature review, qualitative data are collected to identify a broad array of possible antecedents. Then, using a longitudinal survey, the model of consumer shopping intentions and behaviors is validated among 9,992 consumers.Findings>The authors identified antecedents to online shopping related to culture, demographics, economics, technology and personal psychology. Our quantitative analysis showed that the main drivers of online shopping were congruence, impulse buying behavior, value consciousness, risk, local shopping, shopping enjoyment, and browsing enjoyment.Originality/value>The validated model provides a rich explanation of the phenomenon of online shopping that integrates and extends prior work by incorporating new antecedents.
ABSTRACT
Purpose>In the era of the retail Apocalypse, the surge of e-commerce has transmuted the competitive landscape for many traditional retailers that heavily rely on brick-and-mortar stores. This study examines the relationship among retail quality, market environment and businesses' survival in the context of the sporting goods retail industry.Design/methodology/approach>Based on a data set from yelp.com, the authors examine the survival of 1,360 stores within 306 zip codes in the United States using mixed effects logistic modeling.Findings>(1) Retail quality is positively related to survival, but the relationship is nonlinear;(2) the author find a null relationship between market competition and survival, which is subject to several competing interpretations;(3) 10% of the individual variation in survival is due to systematic differences between zip codes and (4) chain stores and stores with more heterogenous reviews have a higher closure rate.Originality/value>This study contributes to the literature by offering an empirical testing of the relationship between retail quality and business survival and examining the impact of trading area in the modern marketing milieu. The findings have practical implications for site selection and designing a service quality program.
ABSTRACT
The pandemic of COVID-19 makes consumers rely on e-commerce to an even higher extent. Since consumers utilize online product reviews (OPRs) for decision making, it is vital to study how various OPR features impact consumer behavior. This research proposes a model for understanding effects of OPR features on consumers’ trust based on HSM. For data collection, we carry out lab experiments and use PLS-SEM analysis to test the model. The results indicate that OPR features influence trust via usefulness of OPRs and attitude toward website. We contribute to the OPR literature by applying the HSM model to the context of OPRs. We also examine the interactions between heuristic mode and systematic mode. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
Purpose>Brick-and-mortar store is an essential channel to deliver a seamless shopping experience and meet customer's dynamic needs in omni-channel retailing. This paper aims to understand customers' expectations of the integrated stores and develop a measurement scale to assess in-store service quality in omni-channel retailing.Design/methodology/approach>Grounded theory methodology (GTM) is employed to obtain a clear picture of consumer expectations and preferences regarding the omni-channel brick-and-mortar integrated stores. Then, an integrated store service quality scale is proposed, refined and validated using a questionnaire survey and structural equation model (SEM).Findings>The measurement scale is set to include seven dimensions: in-store environment, in-store technology, product information consistency, employee assistance, personalization, channel availability and instant gratification and return. The relationships among these seven dimensions and customer satisfaction and loyalty are also verified. According to SEM, product information consistency is more important for customer satisfaction while personalization contributes more to customer loyalty. The results demonstrate that by analysing the seven dimensions, retailers can better understand customers and further improve service quality.Originality/value>This paper proposes a sufficient measurement scale for in-store service quality and fills the gap in omni-channel retailing by capturing its integration attribute.
ABSTRACT
In the Covid-19 pandemic situation, the e-commerce platform has significant data of product reviews in real-Time. Businesses need rating and review systems to immediately expose their consumers' feelings about their products and services and use every volume of data to strengthen their competitive strategies. Amazon is one platform that can provide a vast quantity of product review data. Unfortunately, data from product reviews are typically unstructured and unmanageable. Therefore, this experimental study observed text preprocessing impact to process unstructured product review data using sentiment classifier Decision Tree, Naïve Bayes, and Support Vector Machine (SVM) with better accuracy. The SVM performed higher evaluation model performance, with an accuracy of 88,13%, but the Naïve Bayes classifier has minimum execution time. Furthermore, the experimental result using our approach TF-IDF for feature extraction may significantly improve classification accuracy. As a result, our approach reveals that a good text preprocessing sequence is critical to the classifier's prediction performance for unstructured product review data. © 2021 IEEE.
ABSTRACT
Blockchain technology is considered one of the most revolutionary innovations that has much to offer the tourism industry, having a positive impact among consumers with the help of interactive applications but also easy to use. Tourist services must constantly evolve in a society where the consumer has everything a click away and his requirements are demanding when it comes to quality leisure. Blockchain technology has the power to change the course of the travel experience, offering the customer more autonomy, but the applications developed by the providers can offer transparency and trust to the customers from the moment T0, when the desire to go on a trip is born, until the end at which it should provide feedback. So far, digital and tourism specialists have not agreed on the development of blockchain-based applications, although the benefits are great for both consumers and tourism service providers, as in this publication we can see a series of advantages that blockchain technology can offer the tourism field. This paper also investigates the satisfaction that the Romanian consumer has after purchasing tourist services through e-commerce applications, a satisfaction that can be an additional motivation for specialists to implement blockchain technology. Following the research in this paper, it can be seen how important it is to develop a series of easy-to-use applications, because if the consumer does not manage to use the applications, this affects the degree of satisfaction and the intention to continue using the online applications for the purchase of tourism services.
ABSTRACT
Source: Details available at <https://www.manilatimes. net/2021/05/05/public-square/gida-schools-in-ldn-receive-first-everdigital-st-library/869940/> Library System Offers Free Digital Access to NY Times, WS Journal, Consumer Reports The MDPLS (Miami-Dade Public Library System) has added free unlimited access to The New York Times, The Wall Street Journal and Consumer Reports online to its extensive collection of online digital resources. Patrons can stay informed with access to top-notch news, business, health and lifestyle reporting and more from around the nation and the world with The New York Times and The Wall Street Journal online and become smarter consumers and save money with access to unbiased product reviews, ratings and buying guides for everything from cars and baby gear to appliances and electronics with consumer reports online. According to data provided by the Department of Public Libraries, around 10.9 lakh e-books and 5.49 lakh videos have been accessed so far.