# Guess What's on my Screen? Clustering Smartphone Screenshots with Active Learning

## TL;DR

This paper presents a semi-supervised clustering framework using active learning and multi-modal features to classify large collections of smartphone screenshots with limited labels, aiding media behavior analysis.

## Contribution

It introduces a novel combination of K-Means clustering with active learning and multi-modal feature integration for efficient screenshot classification.

## Key findings

- XGBoost-embedded solutions yield better cluster configurations.
- Multi-modal features improve classification performance.
- Framework reduces manual annotation efforts.

## Abstract

A significant proportion of individuals' daily activities is experienced through digital devices. Smartphones in particular have become one of the preferred interfaces for content consumption and social interaction. Identifying the content embedded in frequently-captured smartphone screenshots is thus a crucial prerequisite to studies of media behavior and health intervention planning that analyze activity interplay and content switching over time. Screenshot images can depict heterogeneous contents and applications, making the a priori definition of adequate taxonomies a cumbersome task, even for humans. Privacy protection of the sensitive data captured on screens means the costs associated with manual annotation are large, as the effort cannot be crowd-sourced. Thus, there is need to examine utility of unsupervised and semi-supervised methods for digital screenshot classification. This work introduces the implications of applying clustering on large screenshot sets when only a limited amount of labels is available. In this paper we develop a framework for combining K-Means clustering with Active Learning for efficient leveraging of labeled and unlabeled samples, with the goal of discovering latent classes and describing a large collection of screenshot data. We tested whether SVM-embedded or XGBoost-embedded solutions for class probability propagation provide for more well-formed cluster configurations. Visual and textual vector representations of the screenshot images are derived and combined to assess the relative contribution of multi-modal features to the overall performance.