AI-driven audience clustering in sport media: a human-computer interaction approach using 'CoPE-DEC'

Area of Science:

• Human-computer interaction
• Artificial intelligence
• Sports media studies

Background:

• Understanding sports media audience behavior is crucial for industry growth.
• Traditional methods struggle to capture complex viewer experience data.
• Integrating HCI and AI offers new avenues for audience analysis.

Purpose of the Study:

• To investigate sports media audience characteristics using AI-driven deep learning.
• To provide foundational data for the sports media industry through audience segmentation.
• To apply a novel unsupervised clustering framework for viewer experience analysis.

Main Methods:

• Utilized a novel Column-conditioned Prototype-Enhanced Deep Embedded Clustering (CoPE-DEC) technique.
• Applied AI-based deep learning analysis to multidimensional viewer experience data.
• Employed unsupervised clustering to identify audience typologies.

Main Results:

• Identified three distinct audience clusters: Sports Value Orientation, Sports Consumption Culture Orientation, and Sports Attitude Orientation.
• Characterized each cluster by unique behavioral, attitudinal, and value-oriented traits.
• Demonstrated the effectiveness of AI and CoPE-DEC in uncovering latent audience structures.

Conclusions:

• AI-driven deep learning, specifically CoPE-DEC, successfully models complex sports media audience segments.
• Findings offer practical implications for personalized content and strategic decision-making in the sports media industry.
• Highlights the interdisciplinary potential of combining HCI, AI, and sports media studies.