Today online networking has become an indispensable part of life for people all over the world. Finally, we demonstrate these techniques in a case study of the development of classifiers for toxic commenting in online communities. We then describe the unique challenges of adapting these concepts for data science work and offer annotator fingerprinting and position mining as promising solutions. We first introduce the concepts of model positionality and computational reflexivity that can help data scientists to reflect on and communicate the social and cultural context of a model's development and use, the data annotators and their annotations, and the data scientists themselves. Drawing from qualitative research practices, we describe how the concepts of positionality and reflexivity can be adapted to provide a framework for understanding, discussing, and disclosing the discretionary choices and subjectivity inherent to data science work. In this paper, we are proposing a Machine Learning framework to filter, detect, and collect cyberstalking evidence on textual data of non-spam emails.ĭata science and machine learning provide indispensable techniques for understanding phenomena at scale, but the discretionary choices made when doing this work are often not recognized. Filtration, Detection, and proper evidence documentation of non-spam email-based cyberstalking are challenging and interesting tasks for researchers. Victims can be easily targeted by cyberstalkers using non-spam email because cyberstalkers often use fake email id and messages which is difficult to block and filter as spam email category. Mostly, through spam email, victims were targeted but in the recent trends, non-spam email is also used by criminals for cyberstalking and cyberbullying. Generally, cybercriminals use fake email IDs either from popular email services providers or from fake email service providers to perform cyber crimes such as phishing, spamming, and cyberstalking. Email is a widely used internet application and is so much popular to share information among people and organizations for personal, business, and official purposes. Like social media, cyberstalkers are using email technology to target the victim as cyberstalking. In modern days of life due to the huge use of Internet technology, cyberstalking has become a major fear for users, society, and institutions. Results indicated that the proposed framework provided significant outcomes, in which the highest percentage of area under curve is 99.24% and F-measure is 97.38% as performed by our trained model.Ĭyberstalking is growing as a social and international problem and creating a pandemic situation for users of internet applications. These features were divided into four groups before being fed into the linear support vector classifier to train our model using ASKfm as data set in hyperparameter tuning and over-sampling environment. Thus, this study proposed a framework with a set of features consisting of word and character term frequency–inverse document frequency and word embedding by using Word2vec and six types of list terms: profane words, proper nouns, negation words, ‘allness’ term, diminisher words and intensifier words. To address this issue, machine learning can be utilised to counter cyberbullying in online social networks. However, this evolution has resulted in people possibly committing various cybercrimes, such as cyberbullying.
Particularly, online social networks have enabled us to connect to one another regardless of time, for as long as we have social media and social networking as platforms for broadcasting information and communicating, respectively. Online social networks have become a necessity to everyone around the world.
0 kommentar(er)
