# Exploring Subjective Tasks in Farsi: A Survey Analysis and Evaluation of Language Models

arXiv: https://arxiv.org/abs/2509.05719 · HTML: https://mlsanity.com/paper/2509.05719/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 6 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance](https://mlsanity.com/paper/2401.03729/) (2024)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Do Multilingual Language Models Think Better in English?](https://mlsanity.com/paper/2308.01223/) (2023)
- [The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions](https://mlsanity.com/paper/2310.12418/) (2023)
- [Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions](https://mlsanity.com/paper/2403.01222/) (2024)
- [SentiPers: A Sentiment Analysis Corpus for Persian](https://mlsanity.com/paper/1801.07737/) (2018)
- [The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis](https://mlsanity.com/paper/2310.12318/) (2023)
- [Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT](https://mlsanity.com/paper/2404.02403/) (2024)
- [FaBERT: Pre-training BERT on Persian Blogs](https://mlsanity.com/paper/2402.06617/) (2024)
- [ArmanEmo: A Persian Dataset for Text-based Emotion Detection](https://mlsanity.com/paper/2207.11808/) (2022)
- [Large Language Models for Subjective Language Understanding: A Survey](https://mlsanity.com/paper/2508.07959/) (2025)
- [A Survey on sentiment analysis in Persian: A Comprehensive System Perspective Covering Challenges and Advances in Resources, and Methods](https://mlsanity.com/paper/2104.14751/) (2021)
- [Emotion Recognition In Persian Speech Using Deep Neural Networks](https://mlsanity.com/paper/2204.13601/) (2022)
- [Sentiment Analysis of Persian-English Code-mixed Texts](https://mlsanity.com/paper/2102.12700/) (2021)
- [A Persian ASR-based SER: Modification of Sharif Emotional Speech Database and Investigation of Persian Text Corpora](https://mlsanity.com/paper/2211.09956/) (2022)
- [Emotion Analysis of Tweets Banning Education in Afghanistan](https://mlsanity.com/paper/2306.16268/) (2023)
- [From Words and Exercises to Wellness: Farsi Chatbot for Self-Attachment Technique](https://mlsanity.com/paper/2310.09362/) (2023)
- [weighted CapsuleNet networks for Persian multi-domain sentiment analysis](https://mlsanity.com/paper/2306.17068/) (2023)

## Abstract (arXiv)

Given Farsi's speaker base of over 127 million people and the growing availability of digital text, including more than 1.3 million articles on Wikipedia, it is considered a middle-resource language. However, this label quickly crumbles when the situation is examined more closely. We focus on three subjective tasks (Sentiment Analysis, Emotion Analysis, and Toxicity Detection) and find significant challenges in data availability and quality, despite the overall increase in data availability. We review 110 publications on subjective tasks in Farsi and observe a lack of publicly available datasets. Furthermore, existing datasets often lack essential demographic factors, such as age and gender, that are crucial for accurately modeling subjectivity in language. When evaluating prediction models using the few available datasets, the results are highly unstable across both datasets and models. Our findings indicate that the volume of data is insufficient to significantly improve a language's prospects in NLP.