Improving sentiment classification using a RoBERTa-based hybrid model
Noura A. Semary, Wesam Ahmed, Khalid Amin, Paweł Pławiak, Mohamed Hammad · 2023
Read Improving sentiment classification using a RoBERTa-based hybrid model by Noura A. Semary, Wesam Ahmed, Khalid Amin, Paweł Pławiak, Mohamed Hammad (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10733963.txt.
Description
Noura Semary, Wesam Ahmed, Khalid Amin, Paweł Pławiak, and Mohamed Hammad blend two neural designs to read feelings in text in this 2023 paper. Sentiment classification, sorting posts into positive or negative, still misses context with single model approaches.
Their hybrid takes sentence vectors from RoBERTa, a refined transformer model, and feeds them to a convolutional network paired with a memory network that reads sequences. The pairing aims to keep the transformer's rich meaning while catching order and local patterns. On movie reviews the model scored about ninety-six percent accuracy, and on airline tweets about ninety-four percent, beating standard methods on both. A resampling trick steadied the lopsided tweet data during training.
Catalog record
| CREATOR | Noura A. Semary, Wesam Ahmed, Khalid Amin, Paweł Pławiak, Mohamed Hammad |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |