Salesken Test for AI/ML Engineer

Zenify: Unveil the Mood of Words with Sentiment Analysis

Black Coffer Assignment

Text analysis, also known as text mining, is the process of automatically classifying and extracting meaningful information from unstructured text. It involves detecting and interpreting trends and patterns to obtain relevant insights from data in just seconds.

Analyze how people perceive plant-based diets online and generate marketing insights on the plant-based products.

Over 30,000 news about Myanmar which were published in 2021 were scrapped from the web and their titles were analyzed.

Media monitoring

A Text Analyzer library tool.

Final course project under the JHU data science course. This app uses a predictive text model built from the large corpus data. The model was built using the tidyverse package and n – gram function. The app was built using the Shiny package and it allows user to enter string and app will predict the next word.

Text analyser

A toolkit for analyzing register, genre and style

"Detect sarcasm effortlessly! This Python app uses NLP and ML to analyze text sentiment, distinguishing sarcastic tones. With a user-friendly interface, input any text for real-time sarcasm identification. Achieve accurate results through advanced sentiment analysis techniques and trained models."

Using Natural Language Processing to understand topic prevalence in oral debates on AI held in the U.S. Congress and European Parliament.

www.fondafan.com

Python >> Text Analytics

Analyzing and processing text implementing various features of spaCy

This repository contains the Text Analysis project from the Applied Data Science course at Columbia University

The KeywordFinder is a project that arose from my vocational school thesis and is being further developed here open source. It is a tool to support text analysis, especially the analysis of tender texts.

L’objectif de cette première partie est de recueillir un jeu de données nettoyé et constitué des mots les plus essentiels et les plus représentatifs et l'identification de la spécificité des données texte, en ce sens qu’elles sont rarement exploitables sous leur forme brute.