Saved in:
Bibliographic Details
Main Authors: Cerit, Merve, Zelikman, Eric, Cho, Mu-Jung, Robinson, Thomas N., Reeves, Byron, Ram, Nilam, Haber, Nick
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.16323
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917995531468800
author Cerit, Merve
Zelikman, Eric
Cho, Mu-Jung
Robinson, Thomas N.
Reeves, Byron
Ram, Nilam
Haber, Nick
author_facet Cerit, Merve
Zelikman, Eric
Cho, Mu-Jung
Robinson, Thomas N.
Reeves, Byron
Ram, Nilam
Haber, Nick
contents As digital media use continues to evolve and influence various aspects of life, developing flexible and scalable tools to study complex media experiences is essential. This study introduces the Media Content Atlas (MCA), a novel pipeline designed to help researchers investigate large-scale screen data beyond traditional screen-use metrics. Leveraging multimodal large language models (MLLMs), MCA enables moment-by-moment content analysis, content-based clustering, topic modeling, image retrieval, and interactive visualizations. Evaluated on 1.12 million smartphone screenshots continuously captured during screen use from 112 adults over an entire month, MCA facilitates open-ended exploration and hypothesis generation as well as hypothesis-driven investigations at an unprecedented scale. Expert evaluators underscored its usability and potential for research and intervention design, with clustering results rated 96% relevant and descriptions 83% accurate. By bridging methodological possibilities with domain-specific needs, MCA accelerates both inductive and deductive inquiry, presenting new opportunities for media and HCI research.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16323
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Media Content Atlas: A Pipeline to Explore and Investigate Multidimensional Media Space using Multimodal LLMs
Cerit, Merve
Zelikman, Eric
Cho, Mu-Jung
Robinson, Thomas N.
Reeves, Byron
Ram, Nilam
Haber, Nick
Human-Computer Interaction
Social and Information Networks
H.5.0; H.5.1; I.2; J.4
As digital media use continues to evolve and influence various aspects of life, developing flexible and scalable tools to study complex media experiences is essential. This study introduces the Media Content Atlas (MCA), a novel pipeline designed to help researchers investigate large-scale screen data beyond traditional screen-use metrics. Leveraging multimodal large language models (MLLMs), MCA enables moment-by-moment content analysis, content-based clustering, topic modeling, image retrieval, and interactive visualizations. Evaluated on 1.12 million smartphone screenshots continuously captured during screen use from 112 adults over an entire month, MCA facilitates open-ended exploration and hypothesis generation as well as hypothesis-driven investigations at an unprecedented scale. Expert evaluators underscored its usability and potential for research and intervention design, with clustering results rated 96% relevant and descriptions 83% accurate. By bridging methodological possibilities with domain-specific needs, MCA accelerates both inductive and deductive inquiry, presenting new opportunities for media and HCI research.
title Media Content Atlas: A Pipeline to Explore and Investigate Multidimensional Media Space using Multimodal LLMs
topic Human-Computer Interaction
Social and Information Networks
H.5.0; H.5.1; I.2; J.4
url https://arxiv.org/abs/2504.16323