thinkingoutloud55's repositories
Aspect-Based-Sentiment-Analysis
A paper list for aspect based sentiment analysis.
AiLearning
AiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP
Aspect-Based-Sentiment-Analysis-1
💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)
contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine BERT with topic models to get coherent topics. Also supports multilingual tasks. Cross-lingual Zero-shot model published at EACL 2021.
glassdoor-company-review-analysis
Springboard Data Science course capstone project 2
Insight-DS-Project
NLP, topic modeling, and sentiment analysis of credit card customer reviews
lda_topic_modeling
Using LDA topic modeling and text features to predict "helpful votes" in Glassdoor reviews.
Multilingual-Text-Classification--XLM-Roberta
To build multilingual models with English-only training data to find the toxicity among Mutilingual Comments
pygrams
Extracts key terminology (n-grams) from any large collection of documents (>1000) and forecasts emergence
pytorch-sentiment-analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
QuantFin
A project for research on asset pricing
sentiment_analysis
project for 224U
SentimentAnalysis
(BOW, TF-IDF, Word2Vec, BERT) Word Embeddings + (SVM, Naive Bayes, Decision Tree, Random Forest) Base Classifiers + Pre-trained BERT on Tensorflow Hub + 1-D CNN and Bi-Directional LSTM on IMDB Movie Reviews Dataset
Text-Mining-Employer-Brand-and-Employee-Satisfaction
The project aims to extract employer characteristics which are helping and hurting employee sentiment towards the employer and aims at providing a single source of truth related to employee satisfaction based on thousands of reviews on Glassdoor
WeSHClass
[AAAI 2019] Weakly-Supervised Hierarchical Text Classification
word2vec-sentiments
Tutorial for Sentiment Analysis using Doc2Vec in gensim (or "getting 87% accuracy in sentiment analysis in under 100 lines of code")