Fine-grained Sentiment Classification using BERT
By Manish Munikar, Sushil Shakya, Aakash Shrestha. 2019
238 citations recorded by the source corpus.
Sentiment classification is an important process in understanding people's perception towards a product, service, or topic. Many natural language processing models have been proposed to solve the sentiment classification problem. However, most of them have focused on binary sentiment classification. In this paper, we use a promising deep learning model called BERT to solve the fine-grained sentiment classification task. Experiments show that our model outperforms other popular models for this task without sophisticated architecture. We also demonstrate the effectiveness of transfer learning in natural language processing in the process.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Soujanya Poria
- Navonil Majumder
- Devamanyu Hazarika
- Rada Mihalcea
- Erik Cambria
- Pascale Fung
- Andrea Madotto
- Zhaojiang Lin
In Natural Language Processing
- Pascale Fung
- Soujanya Poria
- Andrea Madotto
- Devamanyu Hazarika
- Rada Mihalcea
- Kai-Wei Chang
- Zhaojiang Lin
- Navonil Majumder
Citations in the corpus
- BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation (2021, methodology): “Sentiment analysis is commonly used to analyze sentiments in a customer’s reviews or opinions in social media [13, 24].”
- BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements (2020, methodology): “To demonstrate the efficacy of our attack, we evaluate two different types of NLP classification networks, namely LSTM-based classifiers [11] and BERT-based ones [21], using three different benchmark datasets, namely, IMDB [20], Amazon [23], and Stanford Sentiment Treebank (SST-5) dataset [37].”
- Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, methodology): “Models like BERT, XLNet, RoBERTa, and their adaptations have achieved the state-of-the-art performances on multiple sentiment analysis datasets and benchmarks (Hoang et al., 2019; Munikar et al., 2019; Raffel et al., 2019).”
- Plug-and-Play Conversational Models (2020, background): “State-of-the-Art (SotA) results are taken from † (Munikar et al., 2019), ‡ (Kumar et al.”