Social Knowledge Extractor
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.ske-env fix Oct 29, 2017
.vscode saving the score in the db Mar 20, 2017
crawler
data Fixed a bug in the mention count. Jul 6, 2017
knowledge_extractor fixed a typo Jun 26, 2017
model fixed a bug that prevented the pipeline to start. Apr 19, 2017
static fix ui Jul 19, 2017
templates HOTFIX: hardcoded evaluation url to work in locla Feb 9, 2018
test Fixed a bug in the concrete type and added the mention graph Jul 17, 2017
utils fix Oct 29, 2017
.gitignore fixe the gitignore to not included virtualenv folder Feb 19, 2018
LICENSE Initial commit Mar 8, 2017
README.md Update README.md Jun 21, 2017
app.py HOTFIX: hardcoded evaluation url to work in locla Feb 9, 2018
configuration.py fix Oct 29, 2017
oauth.py
orchestrator.py Added a new results page Apr 23, 2017
requirements.txt updated the requirements Jun 21, 2017

README.md

Social Knowledge Extractor

Intro

The Social Knowledge Extractor (SKE) is a software tool that allows to discover new entities using Twitter.

Installation Guide

From the source code

Requirements

Setting up the application

Clone the repository:

git clone https://github.com/DataSciencePolimi/social-knowledge-extractor.git

Inside the SKE folder initialize a python environment

virtualenv ske-env

Activate it

source ske-env/bin/activate

The install the requirements

pip install -r requirements.txt

Setting up the database

The information regarding Dandelion and Twitter are saved in the database.

Thus in order to start to use SKE you need to create in MongoDB a collection named application_keys with the documents

{
  "service" : "dandelion",
  "key_dandelion" : "",
  "app_id" : ""
}

{
  "service" : "twitter",
  "consumer_key" : "",
  "consumer_secret" : ""
}

Run SKE

To run SKE simply launch

python app.py

Using Docker

Requirements

While Docker set up the correct enviroment you still need a Dandelion account and a Twitter application in order to run you own istance of SKE.

TBD

Try the online version

A depolyed version of SKE is available online at here

A tutorial on how to effectively use it is available here