학술논문

Drift in Online Social Media
Document Type
Conference
Source
2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Information Technology, Electronics and Mobile Communication Conference (IEMCON), 2018 IEEE 9th Annual. :302-307 Nov, 2018
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Social network services
Sports
Labeling
Business
Publishing
Measurement
Psychology
Conversation Drift
Chat Drift
Topic Drift
Drift Characteristics
Social Media Drift
Social Media Chat Drift
Language
Abstract
The digital world has opened up a new realm of involvement for people from ages eight to eighty. Online social media and news articles are both vital parts of the modern digital world, where users tend to spend most of their time. Users post comments in online social platforms on various topics and create user engagement through discussions and conversations with other users on a topic in the online platform. User engagement is one of the most important revenue factors of online publishing houses. But, discussion and conversational flow of the topic tends to change and even drift to out-of-topic contexts as different users post in these social platforms. Topic drift can have a significant effect on future user engagement in terms of ‘comments' or ‘likes' and subsequently the revenue metric. In one direction, topic drift towards a totally different area may significantly reduce future user engagement on that article but on the other hand topic drift towards any ‘controversial’ or ‘hot’ topic in that particular time frame can increase future engagement. Thus topic drift is an important phenomena in the online world. In this paper, our aim is to identify how topic flow changes and explore the various characteristics of topic drift and user behavior in online forums.