What question did this study set out to answer?

The aim is to compare multiple neural network models for classifying sentiment in COVID-19-related tweets.

A comparative approach on multiple neural network models aiming to perform a sentiment classification on tweets related to COVID-19 pandemic

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial analyzes sentiment classification of COVID-19 tweets, indicating strong model performance.

The aim is to compare multiple neural network models for classifying sentiment in COVID-19-related tweets.
Analyzed 40,000 tweets from Twitter between March and April 2020.
Preprocessed data using text-cleaning and word-embedding techniques.
Trained and validated six deep learning models including Dense Neural Networks, CNNs, ConvLSTM, and Dense LSTM.
ConvLSTM model achieved an accuracy of 0.8572, precision of 0.8689, recall of 0.8424, and AUC of 0.8894.
The ConvLSTM outperformed baseline and other models in sentiment classification metrics.

Su et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial analyzes sentiment classification of COVID-19 tweets, indicating strong model performance.

The aim is to compare multiple neural network models for classifying sentiment in COVID-19-related tweets.
Analyzed 40,000 tweets from Twitter between March and April 2020.
Preprocessed data using text-cleaning and word-embedding techniques.
Trained and validated six deep learning models including Dense Neural Networks, CNNs, ConvLSTM, and Dense LSTM.
ConvLSTM model achieved an accuracy of 0.8572, precision of 0.8689, recall of 0.8424, and AUC of 0.8894.
The ConvLSTM outperformed baseline and other models in sentiment classification metrics.

Su et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark