Sovereign 8s.is mirror of standardgalactic/COSMO-MT
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
2026-02-26 01:08:17 +05:30
Data_Preprocessing.py Add files via upload 2026-02-18 18:18:55 +05:30
Feature_Vector.py Update Feature_Vector.py 2026-02-26 00:56:04 +05:30
Main.py Add files via upload 2026-02-18 18:24:04 +05:30
README.md Update README.md 2026-02-26 01:08:17 +05:30

Proposed COSMO-MT model

The proposed COSMO-MT model is a new deep learning-based multi-task model to perform Sentiment Classifiction (SC) and Emotion Detection (ED) tasks. It consists of input, embedding, shared and task-specific, dense, and output layers. Each layer is responsible to perform a specific function that supports both SC and ED. In addtion to that four groups of hand-crafted shallow which consist of 15 auxiliary features making the model well-informed. The proposed model is evaluated over two benchmark datasets and it performs significantly better than the comparable methods.

Pre-requisite:

  1. Keras 2.2.4
  2. Numpy
  3. Pandas
  4. Python 3.7
  5. BERT
  6. Tensorflow 1.15
  7. NLTK