Towards a Framework for Acquisition and Analysis of Speeches to Identify Suspicious Contents through Machine Learning

The most prominent form of human communication and interaction is speech. It plays an indispensable role for expressing emotions, motivating, guiding, and cheering. An ill-intentioned speech can mislead people, societies, and even a nation. A misguided speech can trigger social controversy and can r...

Full description

Saved in:
Bibliographic Details
Main Authors: Md. Rashadur Rahman, Mohammad Shamsul Arefin, Md. Billal Hossain, Mohammad Ashfak Habib, A. S. M. Kayes
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2020/5639787
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850110303115673600
author Md. Rashadur Rahman
Mohammad Shamsul Arefin
Md. Billal Hossain
Mohammad Ashfak Habib
A. S. M. Kayes
author_facet Md. Rashadur Rahman
Mohammad Shamsul Arefin
Md. Billal Hossain
Mohammad Ashfak Habib
A. S. M. Kayes
author_sort Md. Rashadur Rahman
collection DOAJ
description The most prominent form of human communication and interaction is speech. It plays an indispensable role for expressing emotions, motivating, guiding, and cheering. An ill-intentioned speech can mislead people, societies, and even a nation. A misguided speech can trigger social controversy and can result in violent activities. Every day, there are a lot of speeches being delivered around the world, which are quite impractical to inspect manually. In order to prevent any vicious action resulting from any misguided speech, the development of an automatic system that can efficiently detect suspicious speech has become imperative. In this study, we have presented a framework for acquisition of speech along with the location of the speaker, converting the speeches into texts and, finally, we have proposed a system based on long short-term memory (LSTM) which is a variant of recurrent neural network (RNN) to classify speeches into suspicious and nonsuspicious. We have considered speeches of Bangla language and developed our own dataset that contains about 5000 suspicious and nonsuspicious samples for training and validating our model. A comparative analysis of accuracy among other machine learning algorithms such as logistic regression, SVM, KNN, Naive Bayes, and decision tree is performed in order to evaluate the effectiveness of the system. The experimental results show that our proposed deep learning-based model provides the highest accuracy compared to other algorithms.
format Article
id doaj-art-427dc74b10f845febbf20953f9db206f
institution OA Journals
issn 1076-2787
1099-0526
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-427dc74b10f845febbf20953f9db206f2025-08-20T02:37:51ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/56397875639787Towards a Framework for Acquisition and Analysis of Speeches to Identify Suspicious Contents through Machine LearningMd. Rashadur Rahman0Mohammad Shamsul Arefin1Md. Billal Hossain2Mohammad Ashfak Habib3A. S. M. Kayes4Department of Computer Science & Engineering, Chittagong University of Engineering & Technology, Chattogram, BangladeshDepartment of Computer Science & Engineering, Chittagong University of Engineering & Technology, Chattogram, BangladeshDepartment of Computer Science & Engineering, Chittagong University of Engineering & Technology, Chattogram, BangladeshDepartment of Computer Science & Engineering, Chittagong University of Engineering & Technology, Chattogram, BangladeshDepartment of Computer Science & Information Technology, La Trobe University, Melbourne, AustraliaThe most prominent form of human communication and interaction is speech. It plays an indispensable role for expressing emotions, motivating, guiding, and cheering. An ill-intentioned speech can mislead people, societies, and even a nation. A misguided speech can trigger social controversy and can result in violent activities. Every day, there are a lot of speeches being delivered around the world, which are quite impractical to inspect manually. In order to prevent any vicious action resulting from any misguided speech, the development of an automatic system that can efficiently detect suspicious speech has become imperative. In this study, we have presented a framework for acquisition of speech along with the location of the speaker, converting the speeches into texts and, finally, we have proposed a system based on long short-term memory (LSTM) which is a variant of recurrent neural network (RNN) to classify speeches into suspicious and nonsuspicious. We have considered speeches of Bangla language and developed our own dataset that contains about 5000 suspicious and nonsuspicious samples for training and validating our model. A comparative analysis of accuracy among other machine learning algorithms such as logistic regression, SVM, KNN, Naive Bayes, and decision tree is performed in order to evaluate the effectiveness of the system. The experimental results show that our proposed deep learning-based model provides the highest accuracy compared to other algorithms.http://dx.doi.org/10.1155/2020/5639787
spellingShingle Md. Rashadur Rahman
Mohammad Shamsul Arefin
Md. Billal Hossain
Mohammad Ashfak Habib
A. S. M. Kayes
Towards a Framework for Acquisition and Analysis of Speeches to Identify Suspicious Contents through Machine Learning
Complexity
title Towards a Framework for Acquisition and Analysis of Speeches to Identify Suspicious Contents through Machine Learning
title_full Towards a Framework for Acquisition and Analysis of Speeches to Identify Suspicious Contents through Machine Learning
title_fullStr Towards a Framework for Acquisition and Analysis of Speeches to Identify Suspicious Contents through Machine Learning
title_full_unstemmed Towards a Framework for Acquisition and Analysis of Speeches to Identify Suspicious Contents through Machine Learning
title_short Towards a Framework for Acquisition and Analysis of Speeches to Identify Suspicious Contents through Machine Learning
title_sort towards a framework for acquisition and analysis of speeches to identify suspicious contents through machine learning
url http://dx.doi.org/10.1155/2020/5639787
work_keys_str_mv AT mdrashadurrahman towardsaframeworkforacquisitionandanalysisofspeechestoidentifysuspiciouscontentsthroughmachinelearning
AT mohammadshamsularefin towardsaframeworkforacquisitionandanalysisofspeechestoidentifysuspiciouscontentsthroughmachinelearning
AT mdbillalhossain towardsaframeworkforacquisitionandanalysisofspeechestoidentifysuspiciouscontentsthroughmachinelearning
AT mohammadashfakhabib towardsaframeworkforacquisitionandanalysisofspeechestoidentifysuspiciouscontentsthroughmachinelearning
AT asmkayes towardsaframeworkforacquisitionandanalysisofspeechestoidentifysuspiciouscontentsthroughmachinelearning