The Impact of Oversampling and Undersampling on Aspect-Based Sentiment Analysis of Indramayu Tourism Using Logistic Regression
Bibliographic record
Abstract
Aspect-based sentiment analysis aims to classify sentiment polarity in opinionated texts based on its associated aspect.However, imbalanced data is a significant challenge that can lead to a decline in classification performance.In machine learning, strategies such as oversampling and undersampling can be implemented to rectify this imbalance.The primary objective of this study is to investigate the impact of data balancing techniques, including oversampling and undersampling, on aspect-based sentiment analysis to enhance classification performance.To achieve this objective, SMOTE, random oversampling, and random undersampling are employed in logistic regression for multi-label classification in aspect-based sentiment analysis.The data for this study was obtained from Google Reviews submitted by individuals who visited the beach in Indramayu.Subsequently, this data was annotated based on tourism-related factors and the sentiments expressed by users.Following this, the data underwent a preprocessing stage and was divided into separate training and test datasets.The training dataset accounted for 60% of the data, while the remaining portion was allocated for testing purposes.During the model training process, data balancing was achieved by implementing oversampling and undersampling techniques and utilizing Logistic Regression with Stochastic Gradient Descent Optimization as the model learning method.The resultant model was subsequently employed to test the test dataset.The evaluation results indicate that oversampling techniques led to a considerable improvement in performance compared to the absence of data balancing.These findings provide a comparison between balancing techniques in sentiment analysis models in tourism that suffer from an imbalanced dataset.Consequently, the oversampling technique can be considered in developing aspect-based sentiment analysis models within the tourism industry.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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".