LEAPMood: Light and Efficient Architecture to Predict Mood with Genetic Algorithm driven Hyperparameter Tuning

TL;DR

LEAPMood introduces a lightweight, on-device deep learning model for mood prediction from textual data, utilizing genetic algorithm-driven hyperparameter tuning to optimize performance and size, with promising results on curated datasets.

Contribution

This paper presents the first on-device deep learning approach for mood prediction from text, combining emotion recognition and clustering, optimized via genetic algorithms for efficiency.

Findings

Achieved 62.05% Micro F1 score on DailyDialog dataset.

Reduced model size by over 90% compared to state-of-the-art.

Curated a new dataset for mood prediction with 72.12% Macro F1-score.

Abstract

Accurate and automatic detection of mood serves as a building block for use cases like user profiling which in turn power applications such as advertising, recommendation systems, and many more. One primary source indicative of an individual's mood is textual data. While there has been extensive research on emotion recognition, the field of mood prediction has been barely explored. In addition, very little work is done in the area of on-device inferencing, which is highly important from the user privacy point of view. In this paper, we propose for the first time, an on-device deep learning approach for mood prediction from textual data, LEAPMood. We use a novel on-device deployment-focused objective function for hyperparameter tuning based on the Genetic Algorithm (GA) and optimize the parameters concerning both performance and size. LEAPMood consists of Emotion Recognition in Conversion (ERC) as the first building block followed by mood prediction using K-means clustering. We show that using a combination of character embedding, phonetic hashing, and attention along with Conditional Random Fields (CRF), results in a performance closely comparable to that of the current State-Of-the-Art with a significant reduction in model size (> 90%) for the task of ERC. We achieve a Micro F1 score of 62.05% with a memory footprint of a mere 1.67MB on the DailyDialog dataset. Furthermore, we curate a dataset for the task of mood prediction achieving a Macro F1-score of 72.12% with LEAPMood.