https://github.com/khip01/sentiment-analysis
sentiment analysis of the Indonesian language
https://github.com/khip01/sentiment-analysis
basic naive-bayes-classifier python rule-based-nlp self-teaching sentiment-analysis
Last synced: 4 days ago
JSON representation
sentiment analysis of the Indonesian language
- Host: GitHub
- URL: https://github.com/khip01/sentiment-analysis
- Owner: Khip01
- Created: 2025-01-07T02:10:27.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-07T04:06:14.000Z (over 1 year ago)
- Last Synced: 2026-07-21T18:38:28.553Z (4 days ago)
- Topics: basic, naive-bayes-classifier, python, rule-based-nlp, self-teaching, sentiment-analysis
- Language: Python
- Homepage:
- Size: 46.9 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Sentiment Analysis
Contains 2 simple projects which have the same goal, which is to analyze sentiment, whether the sentiment is positive, negative or neutral. **The sentiment analyzed is Indonesian sentiment.**
## Rule Based
Rule-based sentiment analysis here is a sentiment analysis method using predefined logic rules. The rules are determined according to the **list of keywords** that have been given in the `words.txt` file whether they are negative or positive words **without using data training**.
## Naive Bayes
Sentiment analysis Naive Bayes here is a technique for analyzing sentiment using the Naive Bayes machine learning method. This method **uses data training to learn the probability of each word appearing in a positive, negative or neutral**.
Which later from the results of the Naive Bayes model will **produce a probability that can later identify a word** including positive or negative or neutral words.
# Instruction
To run either of the projects, we have the same steps:
- go to one of the naive_bayes or rule_based projects with `cd "folder_project_name"`
- create a virtual environment from python first using `python -m venv .venv`
- activate the virtual environment according to your Operating System
- install all the requirement libraries needed by running `pip install requirements.txt`
- run the main.py file with `python -m main`
### Note:
Although this program lacks accuracy in solving problems, it was created for my own personal learning and as an experiment in machine learning.