Перегляд за Автор "Oliinyk, V."
Зараз показуємо 1 - 2 з 2
Результатів на сторінці
Налаштування сортування
- ДокументResearch application of the spam filtering algorithm on social media(2021) Oliinyk, V.Today there are a lot of different social networks and messengers, which in today's society, especially in times of pandemic corona-virus have become an integral part of our daily lives, including work activities. At the same time there is a lot of unnecessary information coming to users every second, so the problem of dealing with spam messages in social networks and messengers is now very relevant. By spam we mean any messages that a person, or an entire company, considers unnecessary in a particular text stream. The project is devoted to solving the scientific and applied problem of detecting spam messages in the text context of any social network or messenger using various spam detection algorithms. Three algorithms were implemented and investigated: an algorithm using naive Bayesian classifier, Support-vector machine and multilayer perceptron neural network. The main idea is to develop a spam detection algorithm that is fast and easy to integrate in a messenger (social network). It is proposed to use the obtained solutions for IT companies. The developed algorithm should recognize spam based on the context of a particular firm and quickly remove or mark it. Since the spam detection task is essentially the task of sorting messages into A and B classes, the developed algorithm can be used not only for spam filtering but also, for example, for monitoring chat rooms for the messages that are important to a particular employee of the company.
- ДокументResearch application of the spam filtering and spammer detection algorithms on social media(2022) Oliinyk, V.There are a bunch of different social networks and messengers today, which in times of pandemic corona-virus have take a really big part of our entire live, especially in our work activities. Besides that, the problem with the spam and spammers is the most relevant than ever, the count of spam in the work text stream is continuously increased. Under spam we understand the text content that is not necessary in the particular text stream, in case of spammer it is meant the person that is sending the spam messages in his or her own purposes. The project was design to solve the scientific and applied problem of detecting spammers and identifying spam messages in the text context of any social network or messenger using various spam detection algorithms and spammer detection approaches. We have implemented 4 algorithms: an algorithm using naive Bayesian classifier, Support-vector machine, multilayer perceptron neural network and convolution neural network. The project was developed in purpose of implementing a spam detection algorithm that is easy to integrate in a messenger (in our case we used Telegram as an example). Design algorithm recognizes spam based on the context of a particular text stream, deletes the spam message and blocks the spammer until one of the application managers unblock the spammer-user. Since the spam detection task is essentially the task of sorting messages into two classes, the usage of the design application is not limited to dealing with spam.