Algorithms for Automated Sentiment Analysis of Posts in Social Networks
Table of Contents
Abstract
Currently, data analysis from social networks is referred to as big data analysis (BigData). The analysis of big data is difficult primarily due to the fact that all the data is fragmented, have different structure and purpose. Nowadays there are no universal algorithms that would allow a full analysis of a social network user’s profile. For the most part, these tools evaluate content quantitatively (how many photos, videos, audio, posts on a user’s page), by the time of user activity, and by the most frequently used words. This article discusses approaches to automating the sentiment analysis of the text content in the social network vk.com, located in public access. Provided an overview of similar studies and a description of different software. This paper examines libraries developed on the basis of machine learning algorithms, as well as algorithms that use tonality dictionaries. The paper compares the probability with which the described algorithms determine the tone of texts. Made the conclusions about the mechanisms of their operation, and given assumptions about the causes of errors are.
-
Author Keywords
- Sentiment analysis,
- data processing,
- social networks,
- neural network
-
Controlled Indexing
- Big Data,
- data analysis,
- learning (artificial intelligence),
- sentiment analysis,
- social networking (online)
-
Non-Controlled Indexing
- big data analysis,
- text content,
- machine-learning algorithms,
- automated sentiment analysis,
- social network user profile
Introduction
Today, social networks are an integral part of our daily life. Their users spend a significant part of their leisure time there, constantly encountering various information. This data is usually selected based on the user’s preferences, but this content may be negative for the person. This topic is particularly relevant in the context of protecting children from negative information. Since the scope of the social network is practically unlimited, the task of manually determining the content properties becomes impossible. Thus, the creation of an automated content analysis system becomes relevant. According to the information in the social network, you can make many different conclusions: determine the preferences of a person, form a psychological portrait of him [1], draw a conclusion about the manner of writing, find artificially written records. This paper describes methods for determining the tonality of a text in the social network vk.com. By text tonality, authors refer to the emotional color of certain elements of the message, the writer’s personal attitude to the problem described by him. In addition, thanks to the methods of determining the tone of content, you can distinguish various forms of propaganda and appeals to extremism, violence, suicide, etc. in the entries on users ‘ pages.
There are many developments that have certain advantages. [2] described the option of training the network on a high-quality dataset, which allowed us to get a high result. The paper [3] describes the experience of carrying out classifications with a large number of experimental parameters. The article [4] contains a detailed description of mathematical models used in machine learning to analyze the totality of texts. In our article revealed the specifics of working with text data collected in social networks.
Conclusion
In the course of conducting experiments on analyzing the tonality of text in social networks using various methods and libraries, the following conclusions were made: algorithms based on classification methods using ready-made dictionaries are not inferior to algorithms based on neural networks;
About KSRA
The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.
KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.
Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.
The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.
FULL Paper PDF file:
Algorithms for Automated Sentiment Analysis of Posts in Social NetworksBibliography
author
Year
2020
Title
Algorithms for Automated Sentiment Analysis of Posts in Social Networks
Publish in
2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT), Yekaterinburg, Russia, 2020, pp. 0361-0363,
Doi
10.1109/USBEREIT48449.2020.9117684.
PDF reference and original file: Click here
Somayeh Nosrati was born in 1982 in Tehran. She holds a Master's degree in artificial intelligence from Khatam University of Tehran.
Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.
Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.
