TY - GEN
T1 - Making online content viral through text analysis
AU - Dilip, R. C.
AU - Lucas, T.
AU - Saarangan, A.
AU - Sumathipala, Sagara
AU - Premachandra, Chinthaka
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/3/26
Y1 - 2018/3/26
N2 - Each and every day there are lots and lots of contents being published on the web. May it be blogs, news articles, movie reviews, product reviews, etc. Although this many number of contents are published, how far a content reaches and engages a large number of expected audience is questionable and unpredictable. Our project aims to solve this issue. The goal of our project is to develop a system that, when a post or textual content is given as an input, makes it to go viral on the web. Our project is the first to propose such a solution for this problem. To make a post go viral, we follow two approaches. First one is to improve the content of the post to incorporate emotions and sentiments. The other one is to take a post directly to its potential audience. The initial step of the first approach is deriving some rules. The next step is where we analyze the actual post, measure its popularity and give suggestions as to how to improve the post in order to make it viral, based on the derived rules. The suggestions will be to replace certain words. The final part is the second approach towards solving the problem. Here, we analyze the social media posts of potential viewers of a post and understand what kind of decisions they may take in the future, so that we can recommend them directly with a certain post. Since we do the system for the domain of movies, we mine the text regarding a user's expectations to watch a certain kind of movie in the near future and recommend him with the reviews about the movie he may likely to watch.
AB - Each and every day there are lots and lots of contents being published on the web. May it be blogs, news articles, movie reviews, product reviews, etc. Although this many number of contents are published, how far a content reaches and engages a large number of expected audience is questionable and unpredictable. Our project aims to solve this issue. The goal of our project is to develop a system that, when a post or textual content is given as an input, makes it to go viral on the web. Our project is the first to propose such a solution for this problem. To make a post go viral, we follow two approaches. First one is to improve the content of the post to incorporate emotions and sentiments. The other one is to take a post directly to its potential audience. The initial step of the first approach is deriving some rules. The next step is where we analyze the actual post, measure its popularity and give suggestions as to how to improve the post in order to make it viral, based on the derived rules. The suggestions will be to replace certain words. The final part is the second approach towards solving the problem. Here, we analyze the social media posts of potential viewers of a post and understand what kind of decisions they may take in the future, so that we can recommend them directly with a certain post. Since we do the system for the domain of movies, we mine the text regarding a user's expectations to watch a certain kind of movie in the near future and recommend him with the reviews about the movie he may likely to watch.
UR - http://www.scopus.com/inward/record.url?scp=85048740946&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048740946&partnerID=8YFLogxK
U2 - 10.1109/ICCE.2018.8326164
DO - 10.1109/ICCE.2018.8326164
M3 - Conference contribution
AN - SCOPUS:85048740946
T3 - 2018 IEEE International Conference on Consumer Electronics, ICCE 2018
SP - 1
EP - 6
BT - 2018 IEEE International Conference on Consumer Electronics, ICCE 2018
A2 - Mohanty, Saraju P.
A2 - Corcoran, Peter
A2 - Li, Hai
A2 - Sengupta, Anirban
A2 - Lee, Jong-Hyouk
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Consumer Electronics, ICCE 2018
Y2 - 12 January 2018 through 14 January 2018
ER -