Summary of Stress Detection on Code-mixed Texts in Dravidian Languages Using Machine Learning, by L. Ramos et al.
Stress Detection on Code-Mixed Texts in Dravidian Languages using Machine Learning
by L. Ramos, M. Shahiki-Tash, Z. Ahani, A. Eponon, O. Kolesnikova, H. Calvo
First submitted to arxiv on: 8 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The study introduces a novel approach to detecting stress in code-mixed texts for Dravidian languages. It focuses on developing robust detection models by using uncleaned text as a benchmark and incorporating diverse preprocessing techniques. The researchers used the Random Forest algorithm with three textual representations: TF-IDF, Uni-grams of words, and a composite of (1+2+3)-Grams of characters. The approach achieved good performance for both linguistic categories, surpassing results from more complex techniques like FastText and Transformer models. This highlights the potential benefits of using uncleaned data and emphasizes the challenges in classifying code-mixed texts for stress detection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Stress is a common feeling that can affect mental well-being. To help identify when someone might be stressed, researchers developed a new way to analyze text messages from people who speak Dravidian languages like Tamil or Telugu. They used two special datasets with examples of text messages in these languages. The team found that using uncleaned text helped them develop better stress-detection models than more complicated techniques like FastText and Transformer models. This shows that using real-life, imperfect data can lead to better results. |
Keywords
» Artificial intelligence » Fasttext » Random forest » Tf idf » Transformer
