Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912572976922624 |
|---|---|
| author | Neumann, Julius Lange, Robert Susanti, Yuni Färber, Michael |
| author_facet | Neumann, Julius Lange, Robert Susanti, Yuni Färber, Michael |
| contents | Sentiment classification in short text datasets faces significant challenges such as class imbalance, limited training samples, and the inherent subjectivity of sentiment labels -- issues that are further intensified by the limited context in short texts. These factors make it difficult to resolve ambiguity and exacerbate data sparsity, hindering effective learning. In this paper, we evaluate the effectiveness of small Transformer-based models (i.e., BERT and RoBERTa, with fewer than 1 billion parameters) for multi-label sentiment classification, with a particular focus on short-text settings. Specifically, we evaluated three key factors influencing model performance: (1) continued domain-specific pre-training, (2) data augmentation using automatically generated examples, specifically generative data augmentation, and (3) architectural variations of the classification head. Our experiment results show that data augmentation improves classification performance, while continued pre-training on augmented datasets can introduce noise rather than boost accuracy. Furthermore, we confirm that modifications to the classification head yield only marginal benefits. These findings provide practical guidance for optimizing BERT-based models in resource-constrained settings and refining strategies for sentiment classification in short-text datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04982 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts Neumann, Julius Lange, Robert Susanti, Yuni Färber, Michael Computation and Language Information Retrieval Machine Learning Sentiment classification in short text datasets faces significant challenges such as class imbalance, limited training samples, and the inherent subjectivity of sentiment labels -- issues that are further intensified by the limited context in short texts. These factors make it difficult to resolve ambiguity and exacerbate data sparsity, hindering effective learning. In this paper, we evaluate the effectiveness of small Transformer-based models (i.e., BERT and RoBERTa, with fewer than 1 billion parameters) for multi-label sentiment classification, with a particular focus on short-text settings. Specifically, we evaluated three key factors influencing model performance: (1) continued domain-specific pre-training, (2) data augmentation using automatically generated examples, specifically generative data augmentation, and (3) architectural variations of the classification head. Our experiment results show that data augmentation improves classification performance, while continued pre-training on augmented datasets can introduce noise rather than boost accuracy. Furthermore, we confirm that modifications to the classification head yield only marginal benefits. These findings provide practical guidance for optimizing BERT-based models in resource-constrained settings and refining strategies for sentiment classification in short-text datasets. |
| title | Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts |
| topic | Computation and Language Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2509.04982 |