Abstract
There is a need for social media platforms to provide a streamlined and seamless experience to share one’s comments on any event or content. The need for community moderation is ever increasing, as well as the need to make the best use of any and all of the huge data generated, in an ethical and responsible manner. The proposed system allows users to mark their responses either by text or by a speech-to-text conversion tool. Thereon, the system classifies the data and initiates corresponding action workflows. Once the data is found not to be platform abuse, the content is reviewed for any sentiment analysis information that could be extracted. In real time, users can express their opinions freely, responsibly, adhering to community standards of information sharing, as well as allow concerned advertising groups to monitor trends and make informed decisions with the user generated data. The system enforces community moderation standards with least manual effort and processes the content uploaded instantly, to provide valuable insight and add commercial value.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
The Guardian (2018) Facebook offers plan to tackle fake news ahead of US midterms. https://www.theguardian.com/technology/2018/mar/29/facebook-fake-news-political-ad-security-us-midterms-2018. Retrieved from 29 March 2018
Business Insider (2018) Facebook is finally launching a new feature to combat fake news, after six months of testing—here’s how it works. https://www.businessinsider.in/Facebook-is-finally-launching-a-new-feature-to-combat-fake-news-after-six-months-of-testing-heres-how-it-works/articleshow/63603421.cms. Retrieved from 4 Apr 2018
Business Standard (2018) Researchers develop new algorithm to detect fake accounts on FB and Twitter. https://www.business-standard.com/article/technology/researchers-develop-new-algorithm-to-detect-fake-accounts-on-fb-and-twitter-118041800601_1.html. Retrieved from 18 Apr 2018
Business Standard (2018) Facebook, Google warn Singapore against new laws to combat fake news. https://www.business-standard.com/article/international/facebook-google-warn-singapore-against-new-laws-to-combat-fake-news-118032201346_1.html. Retrieved from 22 March 2018
Business Standard (2018) Facebook begins ‘fact-checking’ photos, videos to reduce false news stories. https://www.business-standard.com/article/international/facebook-begins-fact-checking-photos-videos-to-reduce-false-news-stories-118033000778_1.html. Retrieved from 30 March 2018
The Washington Post (2018) As Facebook confronts data misuse, foreign governments might force real change. https://www.washingtonpost.com/news/worldviews/wp/2018/04/05/as-facebook-confronts-tough-questions-on-data-misuse-europe-might-force-real-change/?noredirect=on&utm_term=.0a2e0dfd6d74. Retrieved from 4 Apr 2018
The Washington Post (2018) Facebook is now in the data-privacy spotlight. Could Google be next? https://www.washingtonpost.com/news/the-switch/wp/2018/04/11/facebook-is-now-in-the-data-privacy-spotlight-could-google-be-next/?noredirect=on&utm_term=.ebdd054539bc. Retrieved from 11 Apr 2018
BBC News (2018) Social media firms criticised for lack of cyber-bullying action. https://www.bbc.com/news/av/uk-politics-44197761/social-media-firms-criticised-for-lack-of-cyber-bullying-action. Retrieved from 21 May 2018
Bloomberg (2018) U.K. Seeks penalties for tech giants to stop cyber bullying. https://www.bloomberg.com/news/articles/2018-05-20/u-k-seeks-penalties-for-tech-giants-to-stop-cyber-bullying. Retrieved from 20 May 2018
Yu B (2008) An evaluation of text classification methods for literary study. Lit Linguist Comput 23(3):327–343
Tong S, Koller D (2001) Support vector machine active learning with applications to text classification. J Mach Learn Res 2:45–66
Ikonomakis M, Kotsiantis S, Tampakas V (2005) Text classification using machine learning techniques. WSEAS Trans Comput 4(8):966–974
Kaggle, NBC News. The Russian Troll tweets. Retrieved from https://www.kaggle.com/vikasg/russian-troll-tweets
Kaggle, Twitter US Airline Sentiment. Retrieved from https://www.kaggle.com/crowdflower/twitter-airline-sentiment/home
Dalianis H (2018) Computational methods for text analysis and text classification. Clinical text mining. Springer, Cham., pp 83–96
Deng X, Li Y, Weng J, Zhang J (2018) Feature selection for text classification: a review. Multimed Tools Appl pp 1–20
Singh J, Singh G, Singh R, Singh P (2017) Optimizing accuracy of sentiment analysis using deep learning based classification technique. In International conference on recent developments in science, engineering and technology, Springer, Singapore, Oct 2017, pp 516–532
Wang YW, Feng LZ (2018) A new feature selection method for handling redundant information in text classification. Front Inf Technol Electron Eng 19(2):221–234
Sun X, He J (2018) A novel approach to generate a large scale of supervised data for short text sentiment analysis. Multimed Tools Appl, pp 1–21
Acknowledgements
The Data Science Group of 247.ai India is thanked for all the assistance that made this project possible. Sincere thanks are also conveyed to Kaggle and their associated contributors for the data sets sought that were essential to the building of the classifiers.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Aswin, T.S. (2019). Automated Community Feedback and Monitoring Assistant. In: Peng, SL., Dey, N., Bundele, M. (eds) Computing and Network Sustainability. Lecture Notes in Networks and Systems, vol 75. Springer, Singapore. https://doi.org/10.1007/978-981-13-7150-9_28
Download citation
DOI: https://doi.org/10.1007/978-981-13-7150-9_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-7149-3
Online ISBN: 978-981-13-7150-9
eBook Packages: EngineeringEngineering (R0)