Determine the Tonality of of News Media Reports by Conceptual Analysis

2019

Full text Open access: Hybrid Metadata (CSL-JSON)
DOI 10.17759/mda.2019090405
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The article describes the solution of the task of creating linguistic tools and the methodology of automatic determination of the tonality of news reports related to the quality of life of an ordinary citizen of the Republic of Kazakhstan. The approach for solving the problem was defined, software and methods of automated creation of object dictionaries and evaluation predicate dictionaries, as well as evaluation measure modifier dictionaries were developed. The experiment confirmed the correctness of the proposed methodology for assessing events covered in news reports and the operability of the software complex. This technique, with appropriate selection of event assessment objects, can be used in creating tonal portraits of specific authors on the set of their publications, as well as tonal portraits of various news aggregates on the set of events they cover in a particular time interval.