MétaCan
Menu
Back to cohort
Record W4415360479 · doi:10.59934/jaiea.v5i1.1654

Application of Sentiment Analysis on Product Reviews of the Binjai Langkat Buket Shop to Improve Customer Service using the Naive Bayes Method

2025· article· W4415360479 on OpenAlex

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueJournal of Artificial Intelligence and Engineering Applications (JAIEA) · 2025
Typearticle
Language
FieldComputer Science
TopicData Mining and Machine Learning Applications
Canadian institutionsKootenay Association for Science & Technology
Fundersnot available
KeywordsSentiment analysisNaive Bayes classifierPreprocessorProduct (mathematics)Service (business)Data pre-processingTerm (time)Social media

Abstract

fetched live from OpenAlex

In the digital era, customer reviews are spread across various social media and e-commerce platforms, posing a challenge for micro-businesses to evaluate sentiment efficiently. This study aims to develop an automated sentiment analysis system for product reviews of Toko Buket Binjai Langkat using the Term Frequency-Inverse Document Frequency (TF-IDF) method for feature extraction and the Naive Bayes algorithm for positive, negative, and neutral sentiment classification. Data were collected through web scraping techniques and processed with preprocessing stages such as case folding, stopword removal, and stemming. The model was trained and tested with a 70:30 data split and evaluated using accuracy, precision, recall, and F1-score metrics. The test results showed that the model's accuracy reached 91%, with the best performance on positive sentiment (precision 0.89, recall 1.00, F1-score 0.94), but there were limitations in detecting negative sentiment (recall 0.42) due to data imbalance. This study provides practical contributions for micro-businesses in understanding customer opinions and formulating data-driven service improvement strategies.

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.898
Threshold uncertainty score0.739

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.006
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.029
GPT teacher head0.344
Teacher spread0.315 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it