1 of 10

MODEL FOR SEMANTIC ANALYSIS OF INTERNET POSTS��

Olha Kravchenko, Olena Sipko, Rostyslav Lisnevskyi,

Candidates of Technical Sciences, Associate Professors

Andriy Biloshchytskyi

Doctor of Technical Sciences, Professor

Dmytro Syvoglaz

PhD student

1

Dedicated to the tenth anniversary of the Faculty of Information Technology

2 of 10

Introduction

The modern world in Ukraine and other countries is undergoing changes. Humanity has reached the threshold value of information perception. The general ecosystem of human existence is not possible without information technologies and the world of the Internet of Things.
The concept of the IoT ecosystem includes three main levels: the level of information collection, the level of data verification and transmission, and the level of data analytics
The advantages of using the methods of semantic analysis of texts in natural language (Text Mining) for working with textual descriptions of typical attacks and their components contained in the above classification systems are noted. An automated method is proposed for assessing current (i.e., potentially most dangerous) vulnerabilities in industrial control system (ICS) software using semantic analysis methods of descriptions in order to determine a list of threats that are relevant to software vulnerabilities identified at a specific object using security scanners.

3 of 10

Task

The question was to explore the components of the ecosystem and build its architecture.
Develop an ecosystem IT model for semantic analysis of Internet reports.
Check the system for semantic analysis of Internet reports in practice.

4 of 10

Figure 1: IoT ecosystem architecture for semantic analysis of Internet posts

The architecture of the IoT ecosystem depends on the problem to be solved. But in general, the main components of the IoT architecture can be listed.

The components of the IoT architecture are the data acquisition area, the data transmission network, and the data analysis unit (Figure 1).

The data collection area includes the user's gadgets and the user himself. The user (upper left corner of Figure 1) is an integral part of the ecosystem as the initiator of Internet posts [14]. The results of the analysis of Internet posts are sent to the user of the gadget from which the request was made, as a result of the analysis of the Internet post.

The data analysis unit (upper right corner of Figure 1) consists of a database that stores both input and output data, a semantic analysis system, and hardware.

The data transmission network consists of a wired and wireless part of data transmission. The user makes an Internet post using his own gadget. The post is sent to the application database with the help of the Internet. Then, if necessary, the text is analyzed by the semantic text analysis system and sent to the requesting user's gadget.

5 of 10

Figure 2: The algorithm of the bot companion for system semantic analysis internet-topic

6 of 10

IoT model of the system of semantic analysis of Internet posts

Figure 4: Scheme of a part of a neural network for system semantic analysis internet-topic

The neural network used in the system is recurrent. Connects previously obtained results with future results. One of the characteristics of a recurrent neural network is to define an error function for each training step. We will use binary cross-entropy (1) when solving multitask classification.

At the first stage of working with the Internet post, authors turn the text into a combination of zeros and ones. The neural network works with the digital description of the text. Let's turn the text into dense vectors. Each word is a separate token. The neural network learns with the teacher. Therefore, authors compile a test and training data set. The training data set contains answers for semantic analysis of Internet posts for emotional coloring. Figure 4 shows part of the neural network.

At the entrance, get matter 𝑥_𝑡 and return the value ℎ_𝑡. Feedback allows information to be transmitted step by step to each node in the network. The neural network used in the system is recurrent. Connects previously obtained results with future results. One of the characteristics of a recurrent neural network is to define an error function for each training step. We will use binary cross-entropy (1) when solving multitask classification.

7 of 10

The results of testing the neural network

Figure 5: Results of neural network testing

Figure 6: Results of step-by-step analysis of the text

8 of 10

Functional model of the IoT system for the semantic analysis of Internet posts

9 of 10

Analysis of the use of IoT system for the semantic analysis of Internet posts

Figure 8: Results of neural network testing

Figure 9: System performance results IoT system for the semantic analysis of Internet posts

Table 1 An example of a training sample IoT system for the semantic analysis of Internet posts

the text is 94% toxic, 18% moderately toxic, and 84% contains obscene language

Let's download the training sample in .csv format. Table 1 shows an example of a training sample with the following characteristics: ID, text, and emotional coloring of the text.

The emotional coloring of the text presented in Table 1 is represented by 1-presence of emotional coloring, 0- absence of emotional coloring in the text. In the process of learning a neural network under the guidance of a teacher, the following parameters were obtained to obtain an optimal solution:

— the number of epochs — 2 and 5;

— number of iterations for early termination — 250;

— network error calculation — Binary crossentropy;

— learning speed coefficient — 0.05

— optimizer — Adam.

5 epochs are selected for system training. As early as the third epoch, we get stable values from the neural network (Figure 8).

After training, we load the text into the system for analysis. The results of the system are shown in Figure 9

So, the text is 94% toxic, 18% moderately toxic, and 84% contains obscene language.

10 of 10

Summary

The work is devoted to the development of an IoT ecosystem model for the semantic analysis of Internet posts. The need to create an IoT ecosystem that will allow offline assessment of the emotional state of Internet posts is substantiated. The work provides a graphic representation of the IoT ecosystem and describes its components.
The functional model of the IoT system of semantic analysis of Internet posts is described. The principle of learning a neural network, which is the basis of the operation of the IoT system, is presented. The algorithm of the interlocutor bot, which is a means of receiving Internet posts into the system database, is given.
Verification of the work of the IoT system of semantic text analysis was carried out. The result of emotional coloring was obtained with a probability of 94%.
The use of a neural network to determine the emotional color of the Internet and automatically fill the database based on the principles of IoT allows to improve the analysis process. On the basis of research, high accuracy of the emotional color of the short text was obtained. Namely, short text is characteristic of the Internet posts.