Analisis Sentimen Persepsi Masyarakat Terhadap Pemilu 2019 Pada Media Sosial Twitter Menggunakan Naive Bayes
Bibliographic record
Abstract
According to the BAWASLU evaluation a variety of related negative content supports supporting prospective couples to burst into various social media pages. So sometimes the content leads to a hoax issue to the issue of religious and inter-group Racial (SARA). One of the social media used by the people of Indonesia is Twitter, according to Kompas.com number of Twitter daily users globally claimed to be increasing, this appears to be the 3rd Quarter Twitter Financial Report of 2019 on Twitter's 3rd quarter of 2019 Financial reports, daily active users on the Twitter platform are recorded to increase by 17 percent, to the number of 145 million users. So it is necessary that a sentiment analysis study can capture a pattern of community perception on social media Twitter against the 2019 elections and it is expected that this research can help interested parties to increase voter participation rate in the next 5 years. This research method uses the Indonesian tweet data taken from 16 April 2018-16 April 2019, further data in preprocessing, text transformation, stemming Bahasa Indonesia, specifying attribute class, load dictonary and a classification of Naive Bayes using Weka. The conclusion of this study was the classification of Naive Bayes finding that the 2019 election tweet dataset had a negative perception pattern of 52% much greater than the positive perception of 18% and the neutral perception had a value of 31% higher than positive perception. Naive Bayes ' degree of classification accuracy against the training dataset is 81% and the dataset testing 76%, the average precision value for positive sentiment is 86.65%, negative sentiment is 77.15%, and neutral sentiment is worth 80.95% while the average recall rate on positive sentiment is 36.8%, negative sentiment is 93.2% and the neutral sentiment is 86.8%
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".