Measurement of Textual Complexity Based on Categorical Invariance

Lixiao Zhang and Jun Zhang
Additional contact information
Lixiao Zhang: School of Computer Engineering and Science, Shanghai University, Shanghai, China & Shanghai Sanda University, Shanghai, China
Jun Zhang: School of Computer Engineering and Science, Shanghai University, Shanghai, China

International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 2013, vol. 7, issue 2, 80-96

Abstract: Based on the categorical invariance in human concept learning a measurement of textual complexity is proposed. To reach this, transformations of keywords are defined. If a reader grasps the meaning of keywords and the semantic relationship between keywords and sentences, the authors say he/she has understood the text. The transformations of keywords take the difficulty of keywords and the semantic relations between keywords into account. If a text has more common keywords and relations, its complexity is lower. The experiment shows that the measurement is workable. Representational information based on text complexity is to measure the amount of the information in sentences in respect to the whole text. The example shows that the measured information of each sentence is in accordance with the reader’s reading experience.

Date: 2013
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 18/ijcini.2013040106 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jcini0:v:7:y:2013:i:2:p:80-96

Access Statistics for this article

International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) is currently edited by Kangshun Li

More articles in International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) from IGI Global
Bibliographic data for series maintained by Journal Editor ().