# Polarity and Intensity: the Two Aspects of Sentiment Analysis

arXiv: https://arxiv.org/abs/1807.01466 · HTML: https://mlsanity.com/paper/1807.01466/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2018.

## Built on by (most cited first, 8 of 8)

- [Dawn of the transformer era in speech emotion recognition: closing the valence gap](https://mlsanity.com/paper/2203.07378/) (2022)
- [Fair Text-to-Image Diffusion via Fair Mapping](https://mlsanity.com/paper/2311.17695/) (2023)
- [How Personality Traits Influence Negotiation Outcomes? A Simulation based on Large Language Models](https://mlsanity.com/paper/2407.11549/) (2024)
- [MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs](https://mlsanity.com/paper/2505.24423/) (2025)
- [Nostra Domina at EvaLatin 2024: Improving Latin Polarity Detection through Data Augmentation](https://mlsanity.com/paper/2404.07792/) (2024)
- [Quantifying the Effectiveness of Student Organization Activities using Natural Language Processing](https://mlsanity.com/paper/2408.08694/) (2024)
- [Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study](https://mlsanity.com/paper/2610.01046/) (2026)
- [Nobody Truly Agrees on Sentiment: Humans, Bespoke Tools, and LLMs Struggle with Social Media Texts](https://mlsanity.com/paper/2610.10318/) (2026)

## Abstract (arXiv)

Current multimodal sentiment analysis frames sentiment score prediction as a general Machine Learning task. However, what the sentiment score actually represents has often been overlooked. As a measurement of opinions and affective states, a sentiment score generally consists of two aspects: polarity and intensity. We decompose sentiment scores into these two aspects and study how they are conveyed through individual modalities and combined multimodal models in a naturalistic monologue setting. In particular, we build unimodal and multimodal multi-task learning models with sentiment score prediction as the main task and polarity and/or intensity classification as the auxiliary tasks. Our experiments show that sentiment analysis benefits from multi-task learning, and individual modalities differ when conveying the polarity and intensity aspects of sentiment.