Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
This work addresses the problem of creating comprehensive semantic representations of GUI screens and components for data-driven computational methods in GUI design and user interaction modeling, which is an incremental improvement over existing limited representations.
This paper introduces Screen2Vec, a self-supervised technique that generates embedding vectors for GUI screens and components by encoding textual content, visual design, layout patterns, and app contexts from user interaction traces. It demonstrates the utility of these embeddings for tasks such as representing screen similarity, composability, and user tasks.
Representing the semantics of GUI screens and components is crucial to data-driven computational methods for modeling user-GUI interactions and mining GUI designs. Existing GUI semantic representations are limited to encoding either the textual content, the visual design and layout patterns, or the app contexts. Many representation techniques also require significant manual data annotation efforts. This paper presents Screen2Vec, a new self-supervised technique for generating representations in embedding vectors of GUI screens and components that encode all of the above GUI features without requiring manual annotation using the context of user interaction traces. Screen2Vec is inspired by the word embedding method Word2Vec, but uses a new two-layer pipeline informed by the structure of GUIs and interaction traces and incorporates screen- and app-specific metadata. Through several sample downstream tasks, we demonstrate Screen2Vec's key useful properties: representing between-screen similarity through nearest neighbors, composability, and capability to represent user tasks.