Data recommendation engine for a web–based research community social network platform
Social media platforms have gained a large amount of attention as there are many social media applications available for people to use. Some of the social media applications available includes WhatsApp, YouTube, Facebook, Instagram, Twitter, LinkedIn and many others. Based on the statistics of socia...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/76974 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | Social media platforms have gained a large amount of attention as there are many social media applications available for people to use. Some of the social media applications available includes WhatsApp, YouTube, Facebook, Instagram, Twitter, LinkedIn and many others. Based on the statistics of social network penetration in Singapore as of the third quarter of 2017, the top five social media applications are WhatsApp (73%), YouTube (71%), Facebook (70%), Instagram (44%) and Facebook Messenger (42%) (Statista, 2018).
The objective of this Final Year Project (FYP) was to develop a mobile–based intelligent social platform application called AcKuu for different users to share and interact with regards to research and academic activities. The mobile–based intelligent social platform application will include a data–driven recommendation engine.
This report consists of the detailed Methodology, Prototype Design and Implementation and Results of the mobile–based intelligent social platform application and the data–driven recommendation engine. The mobile–based intelligent social platform application was developed using Android Studio and the data–driven recommendation engine will make use of collaborative filtering algorithm.
Overall, the basic functionalities for the mobile–based intelligent social platform application was developed. For the data–driven recommendation engine, dataset was collected and processed for training. |
---|