Algorithms for Automated Sentiment Analysis of Posts in Social Networks

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 any 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 the 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.