Abstract
Sentiment analysis is a major application in natural language processing and is defined as the classification of text into positive, negative and neutral categories. Our work aims to analyse the sentiments of the public on American Presidential impeachment which was approved on 18 December 2019. The data were collected from Twitter using the Twitter API service. The data set had information tweeted about Presidential impeachment but did not have labels which could be used for classification of the text. One of the major problems faced by scientists today is the unavailability of labelled text for training new models. In our research methodology, we test the application of the data programming paradigm on data gathered through Web scrapping, wherein it generates labels based on labelling functions provided by us. The use of these probabilistic labels for classification is termed as weak supervision. It helps to reduce cost and involvement of subject matter experts in labelling the data to create high-quality data sets.
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 New York times what is impeachment process? A step-by-step guide
House Calendar No. 61 H. RES. 755 [Report No. 116–346] 116th congress 1st session
Ratner A, Bach H.S, Ehrenberg H, Fries J, Wu S, Ré C (2017) Snorkel: rapid training data creation with weak supervision. Proc VLDB Endowment 11(3):269–282, 17p
Ratner A, De Sa C, Wu S, Selsam D, Ré C (2016) Data programming: creating large training sets, quickly. Adv Neural Inf Process Syst 29:3567–3575, 27p
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Minaee S, Kalchbrenner N, Cambria E, Nikzad N, Chenaghlu M, Gao J, Deep learning based text classification: a comprehensive review
Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. EMNLP 14:1532–1543. https://doi.org/10.3115/v1/D14-1162
Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space
Acknowledgements
The quality of research in the present is a manifestation of the future of the world. No transformation is possible without scientific innovation and progress. The whole project was built on the foundations laid by the developers of Snorkel which has facilitated us to complete the work efficiently.
Every research project is a result of relentless efforts, critical thinking and innovative approach. Understandably, this project has increased my zeal for learning and zest for research and all this has been possible because of the guidance and motivation of my project guide Rohit Mishra whose empowering directions enabled me to accomplish my task in time. I render my gratitude to him for his co-operation, encouragement and belief in my abilities.
The time spent in reading for the project was exalting and became all the more enriching by my companions Yash, Parth and Vrushabh. My discussions with my co-learners opened vistas of learning for me. I most earnestly wish that every higher school of learning becomes research based in the interest of their nation and of the whole world.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Khaneja, S. (2022). Impeachment and Weak Supervision. In: Aurelia, S., Hiremath, S.S., Subramanian, K., Biswas, S.K. (eds) Sustainable Advanced Computing. Lecture Notes in Electrical Engineering, vol 840. Springer, Singapore. https://doi.org/10.1007/978-981-16-9012-9_33
Download citation
DOI: https://doi.org/10.1007/978-981-16-9012-9_33
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9011-2
Online ISBN: 978-981-16-9012-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)