Hugging Face's logo

Tachygraphy Microtext Normalization by Archisman & Sumon IEMK BTech 2025
non-profit
Activity Feed

AI & ML interests

None defined yet.

Organization Card
Community About org cards

Tachygraphy based Micro-text Analysis And Normalization

Tachygraphy based Micro-text Analysis & Normalization

Welcome to the Tachygraphy based Micro-text Analysis & Normalization Project. This page outlines our project’s key stages, sources, sample analysis examples, and team information.

Dashboard

Project Stages

  1. Sentiment Polarity Analysis
  2. Emotion Mood-tag Analysis
  3. Text Transformation & Normalization
  4. Stacked all 3 stages with their best models
  5. Data Correction & Collection

Sources & Deployment Links

Training Source Kaggle Collections Hugging Face Org
GitHub @ Tachygraphy Micro-text Analysis & Normalization Kaggle Dataset Hugging Face @ Tachygraphy Micro-text Normalization
Deployment Source Streamlit Deployment Hugging Face Space Deployment
GitHub Deployment Repo Streamlit App Hugging Face Space

Project Overview

Tachygraphy—originally developed to expedite writing—has evolved over centuries. In the 1990s, it reappeared as micro‑text, driving faster communication on social media with its “Anytime, Anyplace, Anybody, and Anything (4A)” characteristic. This project focuses on the analysis and normalization of micro‑text (the prevalent informal communication today) to improve NLP tasks such as sentiment analysis, emotion detection, and overall text transformation for clear 4A message decoding.

Sample Example 1

G Input Text Input Text: i don't know fr y he's sooo sad Normalized Text Normalized Text: i do not know for real why he's so sad Input Text->Normalized Text Sentiment Sentiment Input Text->Sentiment Emotion Emotion Input Text->Emotion Negative Negative: 0.995874803543091 Sentiment->Negative Neutral Neutral: 6.232635259628296e-05 Sentiment->Neutral Positive Positive: 2.0964847564697266e-05 Sentiment->Positive Negative->Emotion Neutral->Emotion Positive->Emotion Anger Anger: 0.0 Emotion->Anger Disgust Disgust: 0.0 Emotion->Disgust Fear Fear: 0.010283803842246056 Emotion->Fear Joy Joy: 0.0 Emotion->Joy Neutral_e Neutral: 0.021935827255129814 Emotion->Neutral_e Sadness Sadness: 1.0 Emotion->Sadness Surprise Surprise: 0.02158345977962017 Emotion->Surprise

Sample Example 2

Input Text Input Text: u rlly think all that talk means u tough? lol, when I step up, u ain't gon say sh*t Normalized Text Normalized Text: you really think all that talk makes you tough [lol](laughed out loud) when i step up you are not going to say anything Input Text->Normalized Text Sentiment Sentiment Input Text->Sentiment Emotion Emotion Input Text->Emotion Negative Negative: 0.9999861717224121 Sentiment->Negative Neutral Neutral: 6.885089078423334e-06 Sentiment->Neutral Positive Positive: 1.1117132999061141e-05 Sentiment->Positive Negative->Emotion Neutral->Emotion Positive->Emotion Anger Anger: 0.14403291 Disgust Disgust: 0.039282672 Fear Fear: 0.014349542 Joy Joy: 0.048965044 Neutral_e Neutral: 0.494852662 Sadness Sadness: 0.021111647 Surprise Surprise: 0.237405464 Emotion->Anger Emotion->Disgust Emotion->Fear Emotion->Joy Emotion->Neutral_e Emotion->Sadness Emotion->Surprise

Sample Example 3

Input Text Input Text: bruh, floods in Kerala, rescue ops non-stop 🚁 Normalized Text Normalized Text: Brother, the floods in Kerala are severe, and rescue operations are ongoing continuously. Input Text->Normalized Text Sentiment Sentiment Input Text->Sentiment Emotion Emotion Input Text->Emotion Negative Negative: 4.4367719965521246e-05 Sentiment->Negative Neutral Neutral: 0.9998886585235596 Sentiment->Neutral Positive Positive: 7.097498746588826e-05 Sentiment->Positive Negative->Emotion Neutral->Emotion Positive->Emotion Anger Anger: 0.080178231 Disgust Disgust: 0.015257259 Fear Fear: 0.601871967 Joy Joy: 0.00410547 Neutral_e Neutral: 0.0341026 Sadness Sadness: 0.245294735 Surprise Surprise: 0.019189769 Emotion->Anger Emotion->Disgust Emotion->Fear Emotion->Joy Emotion->Neutral_e Emotion->Sadness Emotion->Surprise