Performance Evaluation of Text Embedding Models for Ambiguity Classification in Indonesian News Corpus: A Comparative Study of TF-IDF, Word2Vec, FastText BERT, and GPT
Bibliographic record
Abstract
Ambiguity in sentence classification is a major challenge in natural language processing (NLP), as it requires a deep understanding of complex semantic contexts.Although various text embedding models have been applied to text classification tasks, comprehensive evaluations of their effectiveness in detecting ambiguous sentences, particularly in Indonesian news corpora, remain limited.This study addresses that gap by comparing the performance of five text embedding models TF-IDF, Word2Vec, FastText, BERT, and GPT combined with five binary classification algorithms: Logistic Regression, Random Forest, bagging, Multinomial Naive Bayes, and Gaussian Naive Bayes.The dataset was derived from the XL-Sum Indonesian news corpus, with sentences automatically labeled as ambiguous or unambiguous using the Claude 3.5 language model.Experimental results show that the combination of Gaussian Naive Bayes with GPT embeddings achieved the best performance in ambiguous sentence classification, with a recall of 71% and an F1score of 60%.Meanwhile, the combination of TF-IDF with bagging yielded the highest accuracy of 83% for unambiguous sentence classification.These findings highlight the critical role of selecting appropriate embedding and classification models to enhance accuracy in semantically ambiguous sentence classification for the Indonesian language.
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 | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".