Semantic Analysis and Text Summarization in Socio-Technical Systems

Semantic Analysis and Text Summarization in Socio-Technical Systems

Nina Rizun (Gdansk University of Technology, Poland)
DOI: 10.4018/978-1-5225-3108-1.ch008
OnDemand PDF Download:
No Current Special Offers


In this chapter, the authors present the results of the development the text-mining methodology for increasing the reliability of the functioning of Socio-technical System (STS). Taking into account revealed strengths and weaknesses of Discriminant and Probabilistic approaches of Latent Semantic Relations analysis in of the abstracting and summarization projection, the Methodology of Two-level Single Document Summarization was developed. The Methodology assumes the following elements of novelty: based on obtaining a multi-level topical framework of the document (abstracting); uses the synergy effect of consistent usage the combination of two approaches for identification of conceptually significant elements of the text (summarization). The examples demonstrating the basic workability of proposed Methodology were presented. Such approaches should help human to increase the quality of supporting the decision-making processes of STS in real time.
Chapter Preview


It is well-known that in conditions of functioning of a human as an element of the Socio-Technical System, it increases:

  • On the one hand, the speed of appearance, accumulation and updating of information;

  • On the other hand, the requirements to the speed of processing the information received by the human (monitoring, analysis and decision-making).

An integral part of the human factor model SHELL in Aviation Systems is the S-Software (rules, documentation, etc.). These components of the model create an information basis for:

  • Training and testing of dispatchers, pilots, other aviation workers;

  • Assessment of flight safety level;

  • Performing of regulated actions in linear (conditioned by clear rules) situations;

  • Justifying the decision-making in nonlinear (unpredictable, non-standard) situations.

At the same time, the speed of processing and understanding of information can often depend not only on the speed of the decision realization, but also on the human’s life. For example, as pointed in (Guide to Methods & Tools for Safety Analysis in Air Traffic Management, 2003; Kharchenko et al., 2014), the process of assessment of flight safety level, threats and hazards is a complex problem and covers a wide spectrum of activities. One of the necessary tools for designing the Integrated safety management system in Air Traffic Services as a Socio-Technical System is the Text Mining technologies. These tools are designed for: automatically extracting structured information from unstructured data; finding the latent relations, patterns and trends within the textual information; text abstracting / summarization.

At the present time, text abstracting and summarization is widely used in Information and Automated Systems to automate the process of extracting key information from the text in the shortest possible time. Usually, automatic abstracting and summarization are considered as independent tasks, although some researchers point out the interdependence of these tasks. The methods of automatic abstracting have much in common with the methods of summarization, although there is a specific characteristic of each of these two classes of problems.

The main purpose of the abstracting is to determine the Topics (with keywords) of the document. Suggestions in which the topics of the document are expressed can be considered as a summary of the meaning of the document. Compilation of the summary (summarization) can begin with the topics identified. But the main purpose of summarization is to extract the key (by topics) words and phrases, taking into account the meaning, find for sentences containing keywords and phrases, and synthesis on this basis of phrases and sentences reflecting the main topics of the text

In any case, the methods of abstracting/summarization can be efficiently used in Automated systems with the aim of:

  • Providing key information in a short time from high-volume data sources for meetings and preparing, forming the reports, organizing the training of Socio-technical System employees;

  • Quick alert of all Aerospace Safety System services in emergency situations.

The purpose of this chapter is to investigate existing methods of Latent Semantic Text Analysis and develop a methodology for text summarization on the basis of the comprehensive use of the approaches of abstracting (topic revealing) and classical summarization.


Theoretical Background

Under the notion of texts mining in natural language we understand the application of methods of texts computer analysis and presentation in order to achieve the quality, which corresponds to the “manual” processing for further usage in various tasks and applications. One of the actual tasks of automatic texts mining is their clustering (definition of groups of the similar documents). More and more often statistical topical methods are being applied (Vorontsov & Potapenko, 2013).

Complete Chapter List

Search this Book: