Earticle

초록

영어

Mobile applications (apps) have become central to the digital economy, yet the proliferation of Dark Patterns—deceptive interface designs hindering user autonomy—increasingly undermines user experience (UX) and trust, posing a significant challenge. While this issue is internationally recognized (e.g., by the OECD), systematic analysis leveraging large-scale app store review data, which captures authentic user voices, to investigate the prevalence of dark patterns and compare their characteristics across service types remains limited. This study addresses this gap by applying text mining techniques to user reviews from major South Korean mobile apps, focusing on leading e-commerce and OTT streaming platforms. The primary objective is to exploratorily identify core complaint themes, keywords, and specific user experience narratives related to Dark Patterns within this dataset. Furthermore, the research aims to deepen the multifaceted understanding of the issue by comparatively analyzing whether distinct patterns of Dark Pattern-related complaints emerge across these different service types. Methodologically, the study involves collecting review data, preprocessing it using Natural Language Processing (NLP), applying LDA topic modeling and keyword analysis to uncover complaint patterns, and qualitatively examining review texts for contextual insights. The findings are expected to provide empirical evidence on the real-world landscape of Dark Pattern issues in the Korean app ecosystem, demonstrating the utility of text mining for this purpose. This research will contribute to the academic discourse on Information Systems (IS) design and UX, while offering practical insights for businesses towards ethical interface improvements and informing future consumer protection policies and regulatory considerations.

목차

Abstract
1. Introduction
2. Literature Review
2.1. Dark Patterns: Concepts, Typology, and Impacts
2.2. App Store Reviews as a Data Source for User Complaint Analysis
2.3. Text Mining and Topic Modeling Methodologies
2.4. Service Type Characteristics: OTT Streaming vs. E-Commerce
2.5. Research Gaps and Contributions
3. Research Framework and Methodology
3.1 Conceptual Framework
3.2 Research Questions
3.3 Data Collection and Analysis
4. Data Collection and Analysis
4.1 Data Collection
4.2 Data Preprocessing
4.3 Text Mining Analysis
4.4 Interpretation and Mapping to Dark Patterns
4.5 Comparative Analysis
5. Results
5.1 Overview of Analyzed Data
5.2 Keyword Frequency and Salience Analysis
5.3 Topic Modeling of User Complaints (LDA Results)
5.4 Mapping Identified Topics to Potential Dark Pattern Categories
5.5 Qualitative Illustrations of Dark Patterns in User Reviews
5.6 Comparative Summary of Complaint Patterns
6. Conclusion
6.1 Implications
6.2 Limitations and Future Research
6.3 Concluding Remarks
References

저자

• 김하늘 [ Department of Business Informatics, Business School, Hanyang University ]
• 신민수 [ Department of Business Informatics, Business School, Hanyang University ] Corresponding Author

참고문헌