Home / Current Issue / Paper 1700409
Predicting Human Well-Being Using Social Media Via Machine Learning
Subject area: Science,Engineering and Technology · Area of research: Computer Engineering
Abstract
Web-based social networking can be named as an online stage where individuals can collaborate with each other for their own or expert interests. There is a major issue of Spam in Social Media where Spam is unimportant or spontaneous messages sent over the Internet, commonly to countless, for the reasons for spreading malware, promoting, and phishing and so on. In this paper, YouTube Spam issue is examined as should be obvious that there are various spam remarks on YouTube which do not have any importance to a specific post or video. To examine a gigantic measure of the dataset, a computerized apparatus is required which is administered by Machine Learning where Machine learning is a kind of Artificial Intelligence (AI) that enables programming applications to wind up more exact in anticipating results without being unequivocally customized. The fundamental start of machine learning is to manufacture calculations that can get input information and utilize measurable investigation to anticipate a yield an incentive inside an adequate range. Machine learning calculations are regularly ordered as being supervised or unsupervised. The dataset is examined based on classification technique of supervised learning. In this interest, different popular existing algorithms are compared and another algorithm is produced utilizing ensembling approach. The best precision accomplished is 76.3%.
Keywords
Social Media, YouTube, Artificial Intelligence, Machine Learning, Ensembling Approach
References
[1] Yang C, Srinivasan P. Life satisfaction and the pursuit of happiness on Twitter. PloS one. 2016 Mar 16;11(3):e0150881.
[2] Dai X, Bikdash M, Meyer B. From social media to public health surveillance: Word embedding based clustering method for twitter classification. InSoutheastCon, 2017 2017 Mar 30 (pp. 1-7). IEEE.
[3] El-Badawy TA, Hashem Y. The impact of social media on the academic development of school students. International Journal of Business Administration. 2014 Dec 16;6(1):46.
[4] Manago AM, Vaughn L. Social media, friendship, and happiness in the millennial generation. InFriendship and Happiness 2015 (pp. 187-206). Springer, Dordrecht.
[5] Lee K, Caverlee J, Webb S. Uncovering social spammers: social honeypots+ machine learning. InProceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval 2010 Jul 19 (pp. 435-442). ACM.
[6] https://www.slideshare.net/pacoid/data- workflows-for-machine-learning
[7] https://www.thebalance.com/what-is-social- media-2890301
[8] https://archive.ics.uci.edu/ml/datasets/ YouTube+Spam+Collection
[9] https://en.wikipedia.org/wiki/AdaBoost
[10] https://en.wikipedia.org/wiki/ Least_squares_support_vector_machine
[11] https://www.r-project.org/about.html
How to cite this paper
@article{1700409,
author = {Shikha Kaushik, Prachi Sharma},
title = {Predicting Human Well-Being Using Social Media Via Machine Learning},
journal = {Iconic Research And Engineering Journals},
year = {2018},
volume = {1},
number = {9},
pages = {329-334},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1700409.pdf},
abstract = {Web-based social networking can be named as an online stage where individuals can collaborate with each other for their own or expert interests. There is a major issue of Spam in Social Media where Spam is unimportant or spontaneous messages sent over the Internet, commonly to countless, for the reasons for spreading malware, promoting, and phishing and so on. In this paper, YouTube Spam issue is examined as should be obvious that there are various spam remarks on YouTube which do not have any importance to a specific post or video. To examine a gigantic measure of the dataset, a computerized apparatus is required which is administered by Machine Learning where Machine learning is a kind of Artificial Intelligence (AI) that enables programming applications to wind up more exact in anticipating results without being unequivocally customized. The fundamental start of machine learning is to manufacture calculations that can get input information and utilize measurable investigation to anticipate a yield an incentive inside an adequate range. Machine learning calculations are regularly ordered as being supervised or unsupervised. The dataset is examined based on classification technique of supervised learning. In this interest, different popular existing algorithms are compared and another algorithm is produced utilizing ensembling approach. The best precision accomplished is 76.3%.},
keywords = {Social Media, YouTube, Artificial Intelligence, Machine Learning, Ensembling Approach},
month = {March},
}