Friend.ly

授权协议 Apache-2.0 License
开发语言 Python
所属分类 神经网络/人工智能、 机器学习/深度学习
软件类型 开源软件
地区 不详
投 递 者 单于智
操作系统 跨平台
开源组织
适用人群 未知
 软件概览



Friend.ly

The internet is flooded with Social Networking Sites(SNS). Be it Twitter, Facebook or Instagram, SNS(s) are without a doubt one of the most popular methods of making friends in the virtual realm. One of the most important aspects of any SNS is the use of a Friend Recommendation System(FRS). Several different types of FRSs have been proposed but a feature that remains common to all of those is homophily, the propensity to associate people with similar others.

While homophily-based FRSs have proven to be extremely accurate in most circumstances, an essential area that still remains relatively unexplored in this domain is the use of personality insights for recommending friends.

With Friend.ly, we propose a novel FRS which leverages text-mining, personality trait extraction, sentiment analysis and hybrid filtering and show it to be having a better performance than most collaborative filtering based FRSs.
Report Bug or Feature Request · Raise a PR

Table of Contents

About The Project

Built With

This project would never have been possible without these wonderful frameworks and project.

Development

This is an example of how you may give instructions on setting up your project locally.To get a local copy up and running follow these simple example steps.

Cloud Setup with GitPod

Gitpod can be used to develop Friend.ly in the cloud. All the commits, if any needs to be made to a branch using convention issue-#(issue-number-on-tracker).

Prerequisites

Clone the repo and hit npm install.

  • npm
npm install

Startup

  1. Clone the repo
git clone https://github.com/und3fined-v01d/Friend.ly
  1. Install NPM packages
npm install
  1. Create a .env file in home directory with valid credentials as follows
TWITTER_CONSUMER_KEY=<your_twitter_consumer_key>
TWITTER_CONSUMER_SECRET=<your_twitter_consumer_secret>
TWITTER_CALLBACK_URL=<your_twitter_callback_url>
GOOGLE_CLIENT_ID=<your_google_client_id>
GOOGLE_CLIENT_SECRET=<your_google_client_secret>
GOOGLE_CALLBACK_URL=<your_google_callback_url>
WATSON_API_KEY=<your_watson_api_key>
WATSON_API_VERSION=<your_watson_api_version>
WATSON_URL=<your_watson_url>
  1. Start the project
npm start

Roadmap

See the open issues for a list of proposed features (and known issues).

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

License

Distributed under the Apache 2.0 License. See LICENSE.md for more information.

Contact

Project Link: https://github.com/und3fined-v01d/Friend.ly

  • 现实生活中场景: 比如QQ空间的相册,我建立了一个私密相册,基本QQ好友都不可见,但是我的私密好友,比如家中女神“老婆”可以访问。如何做到这种越权访问呢?就需要用到友元了,让外部的函数也可以访问我私密类内部的成员。 友元函数的作用: 就是让类外的函数,例如:全局函数,可以访问类内的私有成员变量。 下面举个例子来实现友元函数: #include <iostream> class Person {

  • To my boyfriend Time Limit: 2000/1000 MS (Java/Others)    Memory Limit: 32768/32768 K (Java/Others) Total Submission(s): 1246    Accepted Submission(s): 556 Problem Description Dear Liao I never forge

  • UVA 11722 - Joining with Friend 题目链接 题意:你会在[t1,t2]时刻到,你朋友会在[s1,s2]时刻到,两个人都停留w,问两人碰面的概率 思路:概率题,画图,计算围成面积/总面积就是概率 代码: #include <stdio.h> #include <string.h> int t; double t1, t2, s1, s2, w; double cal

相关阅读

相关文章

相关问答

相关文档