hazm

Your Farsi twitter word cloud here.

🌹 Unsupervised Semantic Clustering of Saadi's Golestan. A Persian NLP project comparing K-Means & DBSCAN algorithms to regroup anecdotes based on semantic similarity using TF-IDF & LSA.

🇮🇷 5-Year Historical Sentiment Analysis of Persian Telegram (~1M posts) using Google Gemma 3 (27B) via Ollama. A deep NLP study on public mood, sarcasm, and cultural nuances (1399–1404 SH).

کدهای مربوط به مقالات آموزشی

persian Ham Spam detector with python, hazm, nltk and nlp.

unsupervised process of identifying topics in a set of persian songs by LDA method of topic modelling

🤖 Tajan – An intelligent bilingual (Persian/English) intent recognition chatbot powered by BiLSTM deep learning. Features: offline Persian/English lemmatizer, smart data augmentation (1.8x), GUI interface, and 419 intent classes with ~66% accuracy. Fully customizable, open-source, and runs without internet. Built with TensorFlow, Hazm, and NLTK.

Persian SnappFood Reviews Sentiment Analysis using TensorFlow, Keras, Hazm, and BiLSTM networks.

Markdown source for Ibn Ḥazm's Kitāb al-Akhlāq wa Siyar.

I use Request Psychological Advice texts in Persian. I clean data and prepare it with the Hazm project. Then cluster them by using Genetic_Kmeans Algorithm and compare results with normal Kmeans and Birch Algorithms.

Simple lexicon-based persian sentiment analysis

In this project, first I start to visualize data in 3 groups to understand better data set, which locate on data_visualization. Second I use hazm library for text processing in Persian data sets on DataCleaning file. Finally, I implement the k-means algorithm for clustering.

Persian Language Processing

A Telegram bot for Persian Moshareh (Poetry Battle) — 666K+ couplets, NLP normalization, hybrid matching.

Corpus building and NLP analysis for Persian Telegram channel messages. Includes a notebook to parse and clean channel_messages.json, stopword normalization, word cloud with a silhouette mask, and CSV outputs (filtered_messages.csv, final_results.csv). Reproducible pipeline for EDA and basic modeling.

End-to-end Persian sentiment analysis using Bidirectional LSTM, Word2Vec, TensorFlow/Keras, and Hazm. Includes data collection, preprocessing, model training, evaluation, and sentiment prediction.

Automatic spell correction for Persian (Farsi) text