Small Stickers, Big Meanings: A Multilingual Sticker Semantic Understanding Dataset with a Gamified Approach

TL;DR

This paper introduces a multilingual sticker query dataset and a gamified annotation framework to improve sticker retrieval and understanding, addressing challenges of subjectivity and dataset construction in visual expression analysis.

Contribution

It presents a novel gamified annotation method, a multilingual sticker query dataset, and fine-tuned models that enhance sticker retrieval and semantic understanding.

Findings

Enhanced query generation quality

Improved retrieval accuracy

Effective semantic understanding

Abstract

Stickers, though small, are a highly condensed form of visual expression, ubiquitous across messaging platforms and embraced by diverse cultures, genders, and age groups. Despite their popularity, sticker retrieval remains an underexplored task due to the significant human effort and subjectivity involved in constructing high-quality sticker query datasets. Although large language models (LLMs) excel at general NLP tasks, they falter when confronted with the nuanced, intangible, and highly specific nature of sticker query generation. To address this challenge, we propose a threefold solution. First, we introduce Sticktionary, a gamified annotation framework designed to gather diverse, high-quality, and contextually resonant sticker queries. Second, we present StickerQueries, a multilingual sticker query dataset containing 1,115 English and 615 Chinese queries, annotated by over 60 contributors across 60+ hours. Lastly, Through extensive quantitative and qualitative evaluation, we demonstrate that our approach significantly enhances query generation quality, retrieval accuracy, and semantic understanding in the sticker domain. To support future research, we publicly release our multilingual dataset along with two fine-tuned query generation models.