cbaziotis/datastories-semeval2017-task4
Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
Implements dual-pathway architecture using stacked LSTMs with attention mechanisms for both message-level and topic-aware sentiment classification on Twitter data. Leverages custom GloVe embeddings trained on 330M tweets (50-300d variants) and the ekphrasis library for Twitter-specific preprocessing, with source code structured in Keras 1.2 for straightforward model inspection and modification.
200 stars. No commits in the last 6 months.
Stars
200
Forks
64
Language
Python
License
MIT
Category
Last pushed
Jun 08, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/cbaziotis/datastories-semeval2017-task4"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codelion/adaptive-classifier
A flexible, adaptive classification system for dynamic text classification
jiegzhan/multi-class-text-classification-cnn-rnn
Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN...
jiegzhan/multi-class-text-classification-cnn
Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN...
iamaziz/ar-embeddings
Sentiment Analysis for Arabic Text (tweets, reviews, and standard Arabic) using word2vec
EveripediaNetwork/fastc
Unattended Lightweight Text Classifiers with LLM Embeddings