# Enhancing ASD detection accuracy: a combined approach of machine learning and deep learning models with natural language processing

arXiv: https://arxiv.org/abs/2403.03581 · HTML: https://mlsanity.com/paper/2403.03581/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 33 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Builds on (most cited first, 5 of 5)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [ASD-DiagNet: A hybrid learning approach for detection of Autism Spectrum Disorder using fMRI data](https://mlsanity.com/paper/1904.07577/) (2019)
- [Traditional Machine Learning Models and Bidirectional Encoder Representations From Transformer (BERT)-Based Automatic Classification of Tweets About Eating Disorders: Algorithm Development and Validation Study](https://mlsanity.com/paper/2402.05571/) (2024)

## Built on by (most cited first, 3 of 3)

- [Copiloting Diagnosis of Autism in Real Clinical Scenarios via LLMs](https://mlsanity.com/paper/2410.05684/) (2024)
- [Classification of Psychiatry Clinical Notes by Diagnosis: A Deep Learning and Machine Learning Approach](https://mlsanity.com/paper/2508.00695/) (2025)
- [The Misclassification of Autistic Writing as AI-Generated](https://mlsanity.com/paper/2607.14729/) (2026)

## Abstract (arXiv)

Purpose: Our study explored the use of artificial intelligence (AI) to diagnose autism spectrum disorder (ASD). It focused on machine learning (ML) and deep learning (DL) to detect ASD from text inputs on social media, addressing challenges in traditional ASD diagnosis. Methods: We used natural language processing (NLP), ML, and DL models (including decision trees, XGB, KNN, RNN, LSTM, Bi-LSTM, BERT, and BERTweet) to analyze 404,627 tweets, classifying them based on ASD or non-ASD authors. A subset of 90,000 tweets was used for model training and testing. Results: Our AI models showed high accuracy, with an 88% success rate in identifying texts from individuals with ASD. Conclusion: The study demonstrates AI's potential in improving ASD diagnosis, especially in children, highlighting the importance of early detection.