Progressive domain adaptation for detecting hate speech on social media with small training set and its application to COVID-19 concerned posts
- 29 July 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Social Network Analysis and Mining
- Vol. 11 (1), 1-18
- https://doi.org/10.1007/s13278-021-00780-w
Abstract
In this world of information and experience era, microblogging sites have been commonly used to express people feelings including fear, panic, hate and abuse. Monitoring and control of abuse on social media, especially during pandemics such as COVID-19, can help in keeping the public sentiment and morale positive. Developing the fear and hate detection methods based on machine learning requires labelled data. However, obtaining the labelled data in suddenly changed circumstances as a pandemic is expensive and acquiring them in a short time is impractical. Related labelled hate data from other domains or previous incidents may be available. However, the predictive accuracy of these hate detection models decreases significantly if the data distribution of the target domain, where the prediction will be applied, is different. To address this problem, we propose a novel concept of unsupervised progressive domain adaptation based on a deep-learning language model generated through multiple text datasets. We showcase the efficacy of the proposed method in hate speech and fear detection on the tweets collection during COVID-19 where the labelled information is unavailable.Keywords
This publication has 45 references indexed in Scilit:
- Domain Adaptive Neural Networks for Object RecognitionLecture Notes in Computer Science, 2014
- Toward a greater understanding of the emotional dynamics of the mortality salience manipulation: Revisiting the “affect-free” claim of terror management research.Journal of Personality and Social Psychology, 2014
- Law enforcement agency adoption and use of Twitter as a crisis communication toolPublished by Elsevier BV ,2012
- Improving a statistical language model through non-linear predictionNeurocomputing, 2009
- Improving predictive inference under covariate shift by weighting the log-likelihood functionJournal of Statistical Planning and Inference, 2000
- Independence, Invariance and the Causal Markov ConditionThe British Journal for the Philosophy of Science, 1999
- Support vector machinesIEEE Intelligent Systems and their Applications, 1998
- Naive (Bayes) at forty: The independence assumption in information retrievalLecture Notes in Computer Science, 1998
- Long Short-Term MemoryNeural Computation, 1997
- Ridge Regression: Applications to Nonorthogonal ProblemsTechnometrics, 1970