Fake_News_Detection_in_Big_Data_Scenario
所属分类:大数据
开发工具:Jupyter Notebook
文件大小:0KB
下载次数:0
上传日期:2023-12-28 09:27:38
上 传 者:
sh-1993
说明: 大数据场景中的假新闻检测(大数据在用课程期末专题)
(Fake News Detection in Big Data Scenario (Final Project of Big Data in Use Course))
文件列表:
.vscode/
Dataset/Raw/VFND/
Document/
Experiment/
Preprocessing/
Script/
Source/
# Final Project - [Course] Big Data in Use
## Information
- Name project: **Fake News Detection in Big Data Scenario**
- Group: Allin
- Instructor: PhD. Nguyn Ngc Tho
- Department: Computer Science
## About repository
This repository contains propsal, tasks, descriptions, source code and other related resources for this course.
## System requirement
## Development Guideline
### Microsoft Azure MongoDB
#### Set up connection
Use following code snippet:
```[Python]
uri = "mongodb://dreamywanderer:fIheB7sQzEsjH3U6WXmOXoVP1Hj79V4Xom1pNV0uHNbNBal0Lx75X6fwSovFOxXFftvFAMsf5SGoACDboPqXRA==@dreamywanderer.mongo.cosmos.azure.com:10255/?ssl=true&retrywrites=false&replicaSet=globaldb&maxIdleTimeMS=120000&appName=@dreamywanderer@"
client = pymongo.MongoClient(uri)
NewsDataset = client['NewsDataset']
```
#### List of Database
- `NewsDataset`: Contains collections of multiple original (raw) dataset. Each dataset belongs to a collection:
- `VNFD`: VNFD dataset.
- `VnExpress`: VnExpress dataset.
- `FakeVN`: FakeVN dataset.
- `VNFDPreprocessed`: The preprocessed VNFD dataset.
### Dataset
#### General dataset scheme
Every crawled dataset before pushed to database need to convert to json with features described in [`Document/denineScheme.md`](https://github.com/DreamyWanderer/Fake_News_Detection_in_Big_Data_Scenario/blob/master/./Document/datasetScheme.md).
#### Specification of each Dataset
There are $3$ datasets we are going to use in this project as training/EDA data.
1. VNFD
2. VnExpress
3. FakeVN
The specification of each above dataset is described in file [`Document/datasetDetail`](https://github.com/DreamyWanderer/Fake_News_Detection_in_Big_Data_Scenario/blob/master/./Document/datasetDetail.md).
### Github Commit Message
Try to follow [Conventional Commits 1.0.0](https://github.com/DreamyWanderer/Fake_News_Detection_in_Big_Data_Scenario/blob/master/https://www.conventionalcommits.org/en/v1.0.0/) and choose type of commits from [here](https://github.com/DreamyWanderer/Fake_News_Detection_in_Big_Data_Scenario/blob/master/https://www.conventionalcommits.org/en/v1.0.0/) when you do a commit. This will help set up the standard and is more easy to follow the repository.
### Misc
I suggest you install CoPilot of Github (Mircrosoft) for quicker coding in some cubersome, tedious or boring tasks.
近期下载者:
相关文件:
收藏者: