Publication Search

This research conducted a systematic literature review of studies related to analyzing service quality based on user reviews with a machine learning approach. A total of 15 international and national journals were analyzed to identify challenges, methods, and trends in research in this aspect. The review results show that Natural Language Processing (NLP) and Sentiment Analysis techniques are the dominant approaches, with machine learning models such as Deep Learning, Naive Bayes, and Support Vector Machine (SVM) being commonly used. The review also identifies research gaps and provides recommendations for future research directions.

Micro, Small, and Medium Enterprises (MSMEs) have a strategic contribution to economic equality and job creation, especially in rural areas. However, limitations in mastering digital technology, especially in marketing, are still a major challenge for MSMEs in Pepelegi Village, Sidoarjo. This community service activity aims to increase the digitalization capacity of MSMEs through training and mentoring in utilizing Google Maps as a promotional media. The method used in this study is Participatory Action Research (PAR), which includes observation, interviews, training, and evaluation. The location of the activity focused on the MSME Warkop Pojok SR in Pepelegi Village, involving the active participation of local business actors. The results of the activity showed an increase in participants' knowledge and skills in creating and managing business profiles on Google Maps. This has a positive impact on business visibility and the potential for increasing income. Digitalization through Google Maps not only makes it easier for consumers to find business locations, but also provides information regarding operating hours, customer reviews, and business contacts. Thus, this activity is expected to be a model for empowering MSMEs based on digital technology that can be replicated in other areas. The sustainability of the program can be strengthened through cross-sector collaboration to support the acceleration of MSME digital transformation.

This study aims to determine the influence of brand image and customer reviews on the purchasing decision of Gambir tea, with price as an intervening variable at UD. Sondel in Pakpak Bharat Regency. This research is quantitative with the population consisting of residents of Pakpak Bharat Regency. The sampling technique used is purposive sampling, with a total of 100 respondents. The data were processed using SPSS version 26, with analysis methods including classical assumption testing, path analysis, Sobel test, and hypothesis testing. The results of the study indicate that: (1) brand image has a direct significant effect on price, (2) customer reviews have a direct significant effect on price, (3) brand image has a direct significant effect on purchasing decisions, (4) customer reviews have a direct significant effect on purchasing decisions, (5) price has a direct significant effect on purchasing decisions, (6) brand image has an indirect significant effect on purchasing decisions through price, and (7) customer reviews have an indirect significant effect on purchasing decisions through price.

This research analyzes user sentiment reviews of the KAI Access application from Google Play Store to improve customer service at PT Kereta Api Indonesia. The study uses a Natural Language Processing (NLP) approach with the Latent Dirichlet Allocation (LDA) algorithm to extract main topics from 10,000 reviews collected from April 2024 to April 2025. Analysis results show 40.7% positive sentiment reviews and 49.3% negative. After data preprocessing through case folding, normalization, tokenization, stopword removal, and stemming, seven optimum topics were found from negative sentiment with a coherence score of 0.508343 and two optimum topics from positive sentiment with a coherence score of 0.511673. Analysis based on five service quality dimensions (tangibles, reliability, responsiveness, assurance, and empathy) reveals that the reliability dimension becomes the main issue, including system instability, transaction failures, login difficulties, and data inaccuracy. The responsiveness dimension is the second priority, with users expecting fast and responsive service to complaints. The results of this study provide recommendations for PT KAI to prioritize improvements in system reliability and responsiveness aspects to enhance the overall user experience, which will ultimately impact customer satisfaction and loyalty.    

The rapid advancement of the internet and social media has led to the emergence of social commerce, which integrates e-commerce with social media platforms. Reviews, as a form of electronic word-of-mouth (e-WOM), have become a key information source relied on by consumers in social commerce. However, the growing presence of buzzers and paid endorsements producing fake reviews has weakened the relevance and trustworthiness of e-WOM, including both online customer reviews and influencer reviews. This study aims to examine the impact of online customer reviews and influencer reviews on the purchase intention of Somethinc products on TikTok’s social commerce platform. The research adopts a quantitative approach with purposive sampling, involving 120 TikTok users in Bandar Lampung as respondents. Data were analyzed using multiple linear regression with SPSS 27 software. The findings reveal that both online customer reviews and influencer reviews significantly and positively influence purchase intention. These results suggest that exposure to online customer and influencer reviews can enhance consumers’ purchase intention toward Somethinc products on TikTok social commerce.

This research is the result of quantitative research which aims to answer questions about the influence of Viral Marketing and online Customer Reviews on the buying interest of Shopee marketing consumers. The research method used is quantitative research and the sampling technique uses a purposive sampling method with a sample size of 98 respondents. The data collection technique uses a questionnaire with the help of a Google form which is processed using SPSS version 27 and the data analysis technique uses multiple linear regression. This research focuses on undergraduate students from the Faculty of Economics and Business, Jambi University as young, dynamic and technology-savvy consumers, who very often use the Shopee e-commerce application to purchase various products. So Shopee has become one of the largest e-commerce which is very popular in Indonesia. The results of this research show that Shopee Viral Marketing has a positive effect on buying interest. Then online Shopee Customer Reviews have a positive effect on buying interest. Furthermore, based on the results of simultaneous test statistical calculations, it shows that Shopee's Viral Marketing and Online Customer Reviews have a simultaneous influence on Shopee marketplace consumer buying interest among undergraduate students at the Faculty of Economics and Business, Jambi University. For the Shopee marketplace, it is recommended to increase Viral Marketing promotions and maintain online Customer Reviews on the Shopee marketplace which is already popular among the public. Apart from that, Shopee also needs to create the latest innovations in order to accommodate customer desires and expectations, in order to maintain competitiveness and product relevance in the market.

This research investigates the impact of brand awareness and online customer reviews on purchase intention regarding Adidas products on the Shopee platform in Indonesia. The research background is founded on the growth of e-commerce and the intense competition present in Indonesia’s fashion industry. A quantitative method employing a survey approach was utilized, engaging 150 Shopee users who are familiar with Adidas products. Data analysis encompassed descriptive tests, classical assumption tests, multiple linear regression, hypothesis testing, and the coefficient of determination, all performed using SPSS version 27. The results demonstrate that brand awareness and online customer reviews have a positive and significant effect on consumer purchase intention, both individually and collectively. These findings imply that greater brand awareness and the quality of reviews are associated with an increase in purchase intention for Adidas products on Shopee. This research offers insights for Adidas Indonesia regarding the significance of enhancing brand awareness and fostering authentic reviews through exclusive promotions, review incentives, and the use of the “Verified Purchase” feature. Future research should be encouraged to integrate additional variables such as price and product quality for a more comprehensive analysis

Marketplace or E-commerce is an internet-based online media as a place to conduct business activities and transactions between buyers and sellers. In the marketplace or e-commerce, buyers can search for as many suppliers as possible with the desired criteria so that they get the appropriate market price. Tokopedia is a marketplace based in Indonesia. The purpose of this study is to explain the role of brand image in mediating the influence of online customer reviews on purchasing decisions. This study was conducted in Denpasar City with a sample of 100 respondents using the non-probability sampling method with the purposive sampling technique. The data analysis technique used is the inferential analysis technique including confirmatory factor analysis (CFA), path analysis, Sobel test and VAF test. The results of this study indicate that online customer reviews have a positive and significant effect on purchasing decisions. Online customer reviews have a positive and significant effect on brand image. Brand image has a positive and significant effect on purchasing decisions. Brand image partially mediates the influence of online customer reviews on purchasing decisions for Tokopedia users in Denpasar City. The implications of this study can be used as consideration and input for Tokopedia in improving consumer purchasing decisions by considering the variables of online customer reviews and brand image.

Shopee, as one of the e-commerce platforms in Indonesia, provides live streaming and online customer review features to increase interaction and product information. This research aims to determine the effect of live streaming and online customer reviews on purchasing decisions among Shopee users among Darul Ulum Islamic Center Sudirman University students. The research method used is quantitative with an associative approach.  The research sample consisted of 100 respondents using a purposive sampling technique. The data collection technique was carried out using a questionnaire distributed via Google Forms.  The research results show that live-streaming shopping and online customer reviews significantly positively influence purchasing decisions among Shopee users among students at Darul Ulum Islamic Center Sudirman University. The adjusted R square value is 0.588. This shows that the independent variables in this research (live streaming shopping and online customer reviews) can explain the dependent variable (purchase decisions) by 58.8%.

The cosmetics industry in Indonesia continues to experience rapid development, especially with increasing consumer preferences for local products. Hanasui, as a local cosmetic brand, offers quality facial serum at affordable prices which is available on various e-commerce platforms. This research aims to analyze the factors that influence consumer behavior in purchasing Hanasui serum, including product quality, price, online reviews and social recommendations. Referring to previous research, factors such as social class, reference groups, product knowledge, and online customer reviews are known to play an important role in cosmetic product purchasing decisions. The findings of this research are expected to provide in-depth insight for manufacturers and marketers to formulate more effective marketing strategies, increase customer loyalty, and strengthen Hanasui's position in the local cosmetics market.  

Customer satisfaction is a crucial indicator in assessing the quality of a company's products, services and overall experience. This research aims to identify the level of customer satisfaction and optimize the available data for effective use in sentiment analysis. In this study, we analyzed 4,353 customer reviews collected over the past year, with 3,481 reviews used as training data and 871 reviews as testing data. The analysis process was conducted using the Cross-Industry Standard Process for Data Mining (CRISP-DM) approach and leveraged the Logistic Regression algorithm to build a predictive model. Model evaluation using the confusion matrix yielded an accuracy of 94.60%, a precision of 94.26%, and a recall of 94.60%. The analysis was conducted using Jupyter Notebook and the Python programming language. The results indicate that sentiment analysis is effective in identifying and predicting customer satisfaction levels, which in turn can help a company’s products improve its service strategies. The optimization of previously underutilized data now provides deeper insights into customer perceptions and expectations, enabling the company to make more targeted decisions and enhance overall customer satisfaction.