Integrating Decision Tree and BIRCH Clustering Algorithms of BERTopic for Analyzing Public Sentiment on Dirtyvote Movie
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This study analyzes public sentiment and topic modeling of YouTube comments on the politically charged film Dirtyvote during Indonesia's election period.Addressing the lack of robust methods for unstructured Indonesian-language social media data, the research proposes an integrative framework.This framework combines a Decision Tree algorithm with Gini Index for interpretable sentiment classification and BERTopic modified with BIRCH clustering to enhance stability and efficiency for large-scale topic modeling.The dataset comprises 76,502 YouTube comments, which were preprocessed to handle noise, informal language, and linguistic variations.Sentiment analysis results demonstrate the superior performance of the Decision Tree with Gini Index, achieving an accuracy of 98.72% and an F1-score of 96%, outperforming other methods such as SVM and Na ve Bayes.Meanwhile, BERTopic with BIRCH clustering achieved higher coherence metrics (e.g., CV, U_Mass, and NPMI) compared to standard BERTopic and K-Means clustering, showcasing its robustness in topic generation.This research contributes methodologically by introducing a scalable and interpretable framework for analyzing unstructured text data in Indonesian.Practically, it offers insights into public opinion dynamics on socio-political issues, highlighting the role of media in shaping perceptions.The findings underline the framework's potential for broader applications in sentiment analysis and topic modeling within diverse socio-political contexts.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it