Walking on air or hopping mad? Understanding the impact of emotions, sentiments and reactions on ratings in online customer reviews of mobile apps

Dhar, Suparna; Bose, Indranil

doi:10.1016/j.dss.2022.113769

Cited by 34 publications

(10 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dataset size [23], [25], [29], [31], [44], [45] <5,000 [20], [22], [26], [30], [43], [46] 5,000-20,000 [24], [36], [38], [47] 20,000-50,000 [21] 50,000-100,000 [33], [34], [35], [40] >100,000 [27], [28], [32], [37], [39], [41], [42] Not available…”

Section: Literaturementioning

confidence: 99%

Text Classification on Customer Feedback: A Systematic Literatures Review

Sidek,

Syed Ahmad,

Kumar

et al. 2024

IJEECS

View full text Add to dashboard Cite

User feedback in text classification serves multiple purposes, including refining models, enhancing datasets, adapting to user preferences, identifying emerging topics, and evaluating system performance, all of which contribute to the creation of more effective and user-centric classification systems. Many text classification techniques, including data mining, machine learning, and deep learning approaches, have been employed in previous literature, each making significant contributions to the field. This paper aims to contribute by guiding researchers seeking commonly used classification techniques and evaluation metrics in text processing. Additionally, it identifies the classification technique that generates higher accuracy and works as a basis for researchers to synthesize studies within their respective fields. PRISMA methodology is adapted to systematically review 28 current literatures on text classification on user feedback. The results obtained are guided by four research questions; paper distribution year, dataset source and size; evaluation metric and model accuracy. The review has shown that support vector machines (SVM) are frequently employed and consistently achieve high levels of accuracy as high as 97.17% with various datasets used. The future direction of this work could explore models that integrate sentiment analysis and natural language understanding to more accurately capture nuanced user opinions and preferences.

show abstract

Section: Literaturementioning

confidence: 99%

Text Classification on Customer Feedback: A Systematic Literatures Review

Sidek,

Syed Ahmad,

Kumar

et al. 2024

IJEECS

View full text Add to dashboard Cite

show abstract

“…Mobile apps, as the new age technology-based services product, are gaining the attention of researchers because of the increasing competition in the apps market, changing patterns of consumer requirements and advancement of mobile technology and the fast technology adoption by mobile apps users (Al-Adwan & Sammour, 2021; Zolkepli, Mukhiar, & Tan, 2021). Some studies have investigated performance expectancy, effort expectancy, social inﬂuence and perceived convenience (Dhar & Bose, 2022; Guo, Peeta, Agrawal, & Benedyk, 2022). Few researchers have investigated the consumer app's likability-related playfulness, access flexibility and connectedness (Chopdar, Korfiatis, Sivakumar, & Lytras, 2018; Li, 2018).…”

Section: Introductionmentioning

confidence: 99%

Exploring the importance of mobile app attributes based on consumers' voices using structured and unstructured data

Bera,

Bhattacharya

2024

IRJMS

View full text Add to dashboard Cite

PurposeThis exploratory study examines and comprehends the relative importance of mobile app attributes from a consumer perspective. Both quantitative and qualitative analysis approaches explore users' behavior and attitudes toward the priorities of mobile app attributes and preferences, identifying correlations between attributes and aggregating individual attributes into groups.Design/methodology/approachOnline convenience sampling and snowball sampling resulted in 417 valid responses. The numerical data are analyzed using the relative to an identified distribution (RIDIT) scoring system and gray relational analysis (GRA), and qualitative responses are investigated using text-mining techniques.FindingsThis study finds enhanced nuances of user preferences and provides data-driven insights that might help app developers and marketers create a distinct app that will add value to consumers. The latent semantic analysis indicates relationship structure among the attributes, and text-based cluster analysis determines the subsets of attributes that represent the unique functions of the mobile app.Practical implicationsThis study reveals the essential components of mobile apps, paying particular attention to the consumer value component, which boosts user approval and encourages prolonged use. Overall, the results demonstrate that developers must concentrate on its functional, technical and esthetic features to make an app more exciting and practical for potential users.Originality/valueMost scholarly research on apps has focused on their technological merits, aesthetics and usability from the user's perspective. A post-adoption multi-attribute app analysis using both structured and unstructured data is conducted in this study.

show abstract

“…Mobile application adoption has received significant attention from researchers in recent years. While some studies have focused on understanding the relationship between mobile app adoption and market value creation by firms (Choudhary et al ., 2022; Dhar and Bose, 2022; Tawira and Ivanov, 2022; Ye et al ., 2022), others have explored the factors that influence customers' continued intention to use mobile apps and their intention to install them (e.g. Chin et al ., 2018; Gu et al ., 2017; Shah et al ., 2022; Sun et al ., 2021; Won et al , 2023).…”

Section: Introductionmentioning

confidence: 99%

The dark side of mobile apps: when and how technical security matters for in-app purchases?

Liu

Chung

Zhang

et al. 2023

APJML

View full text Add to dashboard Cite

PurposeThis research aims to explore the dark side of mobile applications by investigating the role of apps' technicality and app security in the mechanism of user satisfaction, app intention and customers' continuance tendency to make in-app purchases.Design/methodology/approachDrawing on attitude-behavior-context (ABC) theory, the study proposed a conceptual framework and examined the framework using a structural equation modeling (SEM) approach based on data collected from app users from New Zealand.FindingsThe results reveal the correlation between user satisfaction and in-app purchase with a mediator of app continuance intention (ACI). In particular, the results show that app technicality (AT) has a positive correlation with user satisfaction as an antecedent. App security and hedonic value are positively correlated with user satisfaction.Originality/valueThe research has three critical research implications. First, this research advances the understanding of the dark side of mobile apps by showing how app security influences customers' in-app purchases. Secondly, this study reveals and offers empirical evidence for the mechanism between app security and user satisfaction. Finally, the study provides empirical evidence of AT as a distal antecedent for in-app purchases.

show abstract

Walking on air or hopping mad? Understanding the impact of emotions, sentiments and reactions on ratings in online customer reviews of mobile apps

Cited by 34 publications

References 45 publications

Text Classification on Customer Feedback: A Systematic Literatures Review

Text Classification on Customer Feedback: A Systematic Literatures Review

Exploring the importance of mobile app attributes based on consumers' voices using structured and unstructured data

The dark side of mobile apps: when and how technical security matters for in-app purchases?

Contact Info

Product

Resources

About