The researching of the social networks publications classification problem on the subject of positive attitude identification

In article discusses the relevance of solving problems class publication activity analysis for users of social networks. An analysis of existing approaches identifying public opinion about publications in social networks is given, in which the prevalence is substantiated of methods based on the analysis of the texts sentiment. The disadvantages of these methods are given, which reduce the process of assessing public opinion regarding the publication activity of users of social networks efficiency. It is suggested that it is possible to use message metadata without the need a texts sentiment analysis procedure to eliminate this problem. The primary and derived indicators of messages in social networks are determined, obtained from the set of metadata. Approaches to solving the problem of binary classification based on the indicated markers, both based on statistical methods and using machine learning methods, are considered. An assumption is made about the acceptable accuracy of a class of models based on machine learning that provide a solution to the specified problem. A machine learning model based on a random forest is proposed for solving the problem of classifying a positive attitude towards publications in social networks, based on the analysis of primary and derived indicators of messages.

1. Franc V.A. Upravlenie obshchestvennym mneniem: ucheb. Posobie. M-vo obrazovaniya i nauki Ros. Federacii, Ural. feder. un-t. Ekaterinburg: Izd-vo Ural. un-ta. 2016:135.

2. Belikova G.I., Brovkina E.A., Vager B.G., Vitkovskaya L.V., Matveev YU.L. CHislennye metody. Uchebnoe posobie. SPb., RGGMU. 2019:174.

3. Louson CH., Henson R., CHislennoe reshenie zadach metoda naimen'shih kvadratov; Per. s angl. M.: Nauka. Gl. red. fiz.-mat. lit. 1986:232.

4. Fadeev M.A., Markov K.A. CHislennye metody: uchebnoe posobie. NNGU im. N.I. Lobachevskogo. 2010.

5. Samarskij A.A., Gulin A.V. CHislennye metody: uchebnoe posobie dlya vuzov. M.: Nauka. Gl. red. fiz-mat. lit. 1989:432.

6. Davis J., Goadrich M. (2006). The Relationship Between Precision-Recall and ROC Curves. Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA.

7. Budyl'skij D.V. Avtomatizaciya monitoringa obshchestvennogo mneniya na osnove intellektual'nogo analiza soobshchenij v social'nyh setyah: dis. … kand. tekhn. nauk. Bryanskij gos. tekhn. universitet, Bryansk. 2015.

8. Gus'kov S.YU., Lyovin V.V. Interval'nye doveritel'nye ocenki dlya pokazatelej kachestva binarnyh klassifikatorov ROC-krivyh, AUC dlya sluchaya malyh vyborok. Inzhenernyj zhurnal: nauka i innovacii. 2015;3. URL: http://engjournal.ru/catalog/mesc/idme/1376.html.

9. Myuller A., Gvido S. Vvedenie v mashinnoe obuchenie s pomoshch'yu Python. Moskva, 2016-2017.