Summary of Persian Slang Text Conversion to Formal and Deep Learning Of Persian Short Texts on Social Media For Sentiment Classification, by Mohsen Khazeni et al.
Persian Slang Text Conversion to Formal and Deep Learning of Persian Short Texts on Social Media for Sentiment Classification
by Mohsen Khazeni, Mohammad Heydari, Amir Albadvi
First submitted to arxiv on: 9 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: 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 researchers address a crucial gap in the field of sentiment analysis for Persian conversational texts. They develop PSC (Persian Slang Converter), a tool that formalizes informal texts, enabling better machine learning-based sentiment analysis. By leveraging recent deep learning methods and integrating PSC, they improve the accuracy of sentiment classification for short Persian language texts. The team utilizes over 10 million unlabeled texts from various sources and about 10 million news articles to train unsupervised models. They also employ supervised data from Instagram comments (60,000 labeled texts) to fine-tune their emotion classification model. The formalized text conversion yields an impressive 57% accuracy rate. Furthermore, the FastText model and deep LSTM network achieve an accuracy of 81.91% on test data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers created a tool called PSC that helps machines understand Persian texts better. They used old and new ways of learning to make a program that can recognize if someone is happy, sad, or neutral when talking about something. To train the program, they looked at over 10 million texts from different places like social media and movies. They also used labeled texts from Instagram comments to help the program learn. The tool works well, converting most of the informal text into formal language. This helps machines understand Persian texts more accurately. |
Keywords
* Artificial intelligence * Classification * Deep learning * Fasttext * Lstm * Machine learning * Supervised * Unsupervised
