# From Words and Exercises to Wellness: Farsi Chatbot for Self-Attachment Technique

arXiv: https://arxiv.org/abs/2310.09362 · HTML: https://mlsanity.com/paper/2310.09362/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 80 references that are in the map.
- First posted on arXiv 13 Oct 2023.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Rethinking Positional Encoding in Language Pre-training](https://mlsanity.com/paper/2006.15595/) (2020)
- [ParsBERT: Transformer-based Model for Persian Language Understanding](https://mlsanity.com/paper/2005.12515/) (2020)
- [Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity](https://mlsanity.com/paper/2301.12867/) (2023)
- [Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach](https://mlsanity.com/paper/2101.07714/) (2021)
- [A Hybrid Retrieval-Generation Neural Conversation Model](https://mlsanity.com/paper/1904.09068/) (2019)
- [MeDiaQA: A Question Answering Dataset on Medical Dialogues](https://mlsanity.com/paper/2108.08074/) (2021)
- [Emotion Recognition In Persian Speech Using Deep Neural Networks](https://mlsanity.com/paper/2204.13601/) (2022)
- [An Empathetic AI Coach for Self-Attachment Therapy](https://mlsanity.com/paper/2209.08316/) (2022)
- [Low-Resource Adaptation of Open-Domain Generative Chatbots](https://mlsanity.com/paper/2108.06329/) (2021)
- [Persian Emotion Detection using ParsBERT and Imbalanced Data Handling Approaches](https://mlsanity.com/paper/2211.08029/) (2022)

## Built on by (most cited first, 2 of 2)

- [Exploring Subjective Tasks in Farsi: A Survey Analysis and Evaluation of Language Models](https://mlsanity.com/paper/2509.05719/) (2025)
- [Structure Matters: Evaluating Multi-Agents Orchestration in Generative Therapeutic Chatbots](https://mlsanity.com/paper/2603.00774/) (2026)

## Abstract (arXiv)

In the wake of the post-pandemic era, marked by social isolation and surging rates of depression and anxiety, conversational agents based on digital psychotherapy can play an influential role compared to traditional therapy sessions. In this work, we develop a voice-capable chatbot in Farsi to guide users through Self-Attachment (SAT), a novel, self-administered, holistic psychological technique based on attachment theory. Our chatbot uses a dynamic array of rule-based and classification-based modules to comprehend user input throughout the conversation and navigates a dialogue flowchart accordingly, recommending appropriate SAT exercises that depend on the user's emotional and mental state. In particular, we collect a dataset of over 6,000 utterances and develop a novel sentiment-analysis module that classifies user sentiment into 12 classes, with accuracy above 92%. To keep the conversation novel and engaging, the chatbot's responses are retrieved from a large dataset of utterances created with the aid of Farsi GPT-2 and a reinforcement learning approach, thus requiring minimal human annotation. Our chatbot also offers a question-answering module, called SAT Teacher, to answer users' questions about the principles of Self-Attachment. Finally, we design a cross-platform application as the bot's user interface. We evaluate our platform in a ten-day human study with N=52 volunteers from the non-clinical population, who have had over 2,000 dialogues in total with the chatbot. The results indicate that the platform was engaging to most users (75%), 72% felt better after the interactions, and 74% were satisfied with the SAT Teacher's performance.