Sentiment analysis of extremism in social media from textual information

Bengali abusive text detection can be useful to prevent cyberbullying and online harassment as these types of crimes are increasing rapidly in Bangladesh Machine learning approach can be useful to keep the system always updated with the new types of approaches used by the abusers This paper investigates machine learning algorithms eg Random Forest, Multinomial Naive Bayes, Support Vector Machine (SVM) with Linear, Radial Basis Function (RBF), Polynomial and Sigmoid kernel and have compared with unigram, bigram and trigram based CountVectorizer and TfidfVectorizer features The results show that SVM Linear kernel performs the best with trigram TfidfVectorizer features

/pdf/an-application-of-machine-learning-to-detect-abusive-bengali-2xll8bj4is.pdf

An application of machine learning to detect abusive Bengali text

Text classification is a common task in machine learning. One of the supervised classification algorithm called Random Forest has been generally used for this task. There is a group of parameters in Random Forest classifier which need to be tuned. If proper tuning is performed on these hyperparameters, the classifier will give a better result. This paper proposes a hybrid approach of Random Forest classifier and Grid Search method for customer feedback data analysis. The tuning approach of Grid Search is applied for tuning the hyperparameters of Random Forest classifier. The Random Forest classifier is used for customer feedback data analysis and then the result is compared with the results which get after applying Grid Search method. The proposed approach provided a promising result in customer feedback data analysis. The experiments in this work show that the accuracy of the proposed model to predict the sentiment on customer feedback data is greater than the performance accuracy obtained by the model without applying parameter tuning.

/pdf/grid-search-tuning-of-hyperparameters-in-random-forest-5ekbc2mks6.pdf

Grid Search Tuning of Hyperparameters in Random Forest Classifier for Customer Feedback Sentiment Prediction

In the past few years, retail market industries have taken a broad form to sell the products online and also to give the opportunity to customers to provide their valuable feedbacks, suggestions and recommendations. The aim of this paper is to provide an automatic comment analyzer. And propose an automatic comment analyzer and classification system which can determine the polarity of the customer comments collected from Amazon and Flipkart data domains effectively. This system should be able to process the large number of reviews. It should categorize the comments as positive, negative and neutral classes using five prime supervised learning classifiers such as NB, LR, SentiWordNet, RF and KNN. The paper also discusses their experimental results and challenges found. Therefore, this study shows the maximum usage of feature extraction, positive–negative sentiment, Amazon web source, mobile phone for a large set of reviews in the existing algorithms. It included the preliminary definitions, information extraction and retrieval aspects, role of machine learning, and the comment mining. The comment analysis and classification described comment polarity, orientation, subjectivity detection, comment analysis, summarization and classification. The classification of comment analysis techniques explained various lexicons and supervised algorithms along with the essential used-based concerns.

Sentiment Analysis of Amazon Product Reviews Using Hybrid Rule-Based Approach

The online web tools enable everyone who can confidently voice their opinions in public sphere. The opinion may be encouragement, blessing or good suggestion i.e. positive, or it may be negative to that extent that it must be restricted at some point. The aim of this paper is to survey the different machine learning techniques employed within the scope of discovering the hateful language on social networking site, their challenges to provide a solution to detect the toxic comment and modify it of the same.

http://www.ijarcs.info/index.php/Ijarcs/article/download/3506/3459

Toxic Comment Tools: A Case Study

Text recognition in images is a research area which attempts to develop a computer system with the ability to automatically read the text from images These days there is a huge demand in storing the information available in paper documents format in to a computer storage disk and then later reusing this information by searching process One simple way to store information from these paper documents in to computer system is to first scan the documents and then store them as images But to reuse this information it is very difficult to read the individual contents and searching the contents form these documents line-by-line and word-by-word The challenges involved in this the font characteristics of the characters in paper documents and quality of images Due to these challenges, computer is unable to recognize the characters while reading them Thus there is a need of character recognition mechanisms to perform Document Image Analysis (DIA) which transforms documents in paper format to electronic format In this paper we have discuss method for text recognition from images The objective of this paper is to recognition of text from image for better understanding of the reader by using particular sequence of different processing module

Text recognition from images

Social Network has become a place where people from every corner of the world has established a virtual civilization. In this virtual community, people used to share their views, express their feelings, photos, videos, blogs, etc. Social Networking Sites like Facebook, Twitters, etc. has given a platform to share innumerable contents with just a click of a button. However, there is no restriction applied by them for the uploaded content. These uploaded content may contains abusive words, explicit images which may be unsuitable for social platforms. As such there is no defined mechanism for restricting offensive contents from publishing on social sites. To solve this problem we have used our proposed approach. In our approach we are developing a social network prototype for implementing our approach for automatic filtering of offensive content in social network. Many popular social networking sites today don't have proper mechanism for restricting offensive contents. They use reporting methods in which user report if the content is abuse. This requires substantial human efforts and time. In this paper, we applied pattern matching algorithm for offensive keyword detection from social networking comments and prevent it from publishing on social platform. Apart from conventional method of reporting abusive contents by users our approach does not requires any human intervention and thus restrict offensive words by detecting and preventing it automatically.

An approach for offensive text detection and prevention in Social Networks

Social Network has become an integral part of 21st Century Generation It has touched every individual's life in one or the other way Daily tons of information is being shared on different social network platform These sites provide various means for uploading and publishing the contents These contents are being shared in various forms such as Text, Images, Videos, etc These uploaded content may contains abusing words, explicit images which may be unsuitable for social platforms As such there is no proper mechanism for restricting offensive contents from publishing it on these sites These problems gave rise to an idea for our proposed approach In our approach we are developing a prototype of social network platform in which we will apply some filtering mechanism to the uploaded contents and prevent them from publishing on social network platform It basically focuses on text filtration and image filtration for any abusive and explicit content respectively In this paper, we have done a survey on different text categorization techniques and algorithms used for text categorization We started our survey by studying various text categorization techniques used for recognizing of offensive texts Further, we studied various algorithms for implementing these techniques into our prototype

Shashank H. Yadav

Papers

Text recognition from images

An approach for offensive text detection and prevention in Social Networks

A survey on different text categorization techniques for text filtration