Cost-Effective Tweet Classification through Transfer Learning in Low-Resource NLP Settings
Bibliographic record
Abstract
Recently, pre-trained Transformer-based Language Models (TLM) for specific task has led to significant advancements in Natural Language Processing (NLP) tasks, achieving state-of-the-art results. Despite the ability of TLM and its benefits for low-resource languages where labelled data is scarce. Limited research has been conducted on investigating the applicability of TLM in low-resource settings for French tweets classification. In this paper, our focus is on exploring the effectiveness of Transfer Learning using fine-tuned Transformer language models, specifically FlauBERT and XLM-RoBERTa applied to French tweet dataset. We investigate their ability to achieve higher performance in text classification tasks while requiring less training data compared to traditional text classification methods.Experiments conducted on our labeled dataset consisting of 4000 French tweets reveal that FlauBERT outperforms its rival, achieving an average F1-score of 0.84 compared to XLM-R’s 0.79. However, in scenarios with even fewer available data, XLM-R has the potential to surpass FlauBERT.Furthermore, the environmental sustainability is considered while highlighting the potential CO2emissions reduction through manipulating the layers of FlauBERT without compromising the performance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".