# Understanding Chat Messages for Sticker Recommendation in Messaging Apps

arXiv: https://arxiv.org/abs/1902.02704 · HTML: https://mlsanity.com/paper/1902.02704/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

## Built on by (most cited first, 6 of 6)

- [Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark](https://mlsanity.com/paper/2109.01839/) (2021)
- [CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling](https://mlsanity.com/paper/2309.05270/) (2023)
- [Overview of Memotion 3: Sentiment and Emotion Analysis of Codemixed Hinglish Memes](https://mlsanity.com/paper/2309.06517/) (2023)
- [Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selection](https://mlsanity.com/paper/2511.17587/) (2025)
- [Selecting Stickers in Open-Domain Dialogue through Multitask Learning](https://mlsanity.com/paper/2209.07697/) (2022)
- [PerSRV: Personalized Sticker Retrieval with Vision-Language Model](https://mlsanity.com/paper/2410.21801/) (2024)

## Abstract (arXiv)

Stickers are popularly used in messaging apps such as Hike to visually express a nuanced range of thoughts and utterances to convey exaggerated emotions. However, discovering the right sticker from a large and ever expanding pool of stickers while chatting can be cumbersome. In this paper, we describe a system for recommending stickers in real time as the user is typing based on the context of the conversation. We decompose the sticker recommendation (SR) problem into two steps. First, we predict the message that the user is likely to send in the chat. Second, we substitute the predicted message with an appropriate sticker. Majority of Hike's messages are in the form of text which is transliterated from users' native language to the Roman script. This leads to numerous orthographic variations of the same message and makes accurate message prediction challenging. To address this issue, we learn dense representations of chat messages employing character level convolution network in an unsupervised manner. We use them to cluster the messages that have the same meaning. In the subsequent steps, we predict the message cluster instead of the message. Our approach does not depend on human labelled data (except for validation), leading to fully automatic updation and tuning pipeline for the underlying models. We also propose a novel hybrid message prediction model, which can run with low latency on low-end phones that have severe computational limitations. Our described system has been deployed for more than 6 months and is being used by millions of users along with hundreds of thousands of expressive stickers.