Clause Analysis: Using Syntactic Information to Automatically Extract Source, Subject, and Predicate from Texts with an Application to the 2008–2009 Gaza War

Abstract

This article presents a new method and open source R package that uses syntactic information to automatically extract source–subject–predicate clauses. This improves on frequency-based text analysis methods by dividing text into predicates with an identified subject and optional source, extracting the statements and actions of (political) actors as mentioned in the text. The content of these predicates can be analyzed using existing frequency-based methods, allowing for the analysis of actions, issue positions and framing by different actors within a single text. We show that a small set of syntactic patterns can extract clauses and identify quotes with good accuracy, significantly outperforming a baseline system based on word order. Taking the 2008–2009 Gaza war as an example, we further show how corpus comparison and semantic network analysis applied to the results of the clause analysis can show differences in citation and framing patterns between U.S. and English-language Chinese coverage of this war.

Taxis and Logico-Semantic Relation in undergraduate Students’ English Theses Writing Text: A Systemic Functional Linguistics Approach

“…The relation of clauses shows "logical" components of the linguistics system that is semantic relation which make up the logic of natural language (Halliday M. , 1994, p. 216). There have been many studies relating to clauses or clauses relation conducted by researchers, such as (Atteveldt, 2016), Clauses Analysis; (Martin, 2014). Evolving systemic functional linguistics: beyond the clause; (Tam, 2013), The Notion of Clause Complex; (Farinde, 2015), Functional Values of English clause; (Barker, 1996), Clause -level relationship; and (Holsting, 2008),Projecting Clause Complexes and the Subjunctive Mood.…”

Text Analysis in R

“…Dictionaries are also a popular approach for measuring sentiment (De Smedt & Daelemans, 2012;Mostafa, 2013;Taboada, Brooke, Tofiloski, Voll, & Stede, 2011) as well as other dimensions of subjective language (Tausczik & Pennebaker, 2010). By combining this type of analysis with information from advanced NLP techniques for identifying syntactic clauses, it also becomes possible to perform more fine-grained analyses, such as sentiment expressions attributed to specific actors (Van Atteveldt, 2008), or actions and affections from one actor directed to another (Van Atteveldt, Sheafer, Shenhav, & Fogel-Dror, 2017).…”

“…Also, since "Smith" is the nominal subject (nsubj) of the verb "gave", and Alice is the dative case (dative) we know that "Bob Smith" is the one who gives to "Alice". This type of information can for instance be used to analyze who is attacking whom in news coverage about the Gaza war (Van Atteveldt et al, 2017).…”

“…Third, each token can be annotated with token specific information, such as obtained from advanced NLP techniques. This enables, for instance, the use of dependency parsing to perform an analysis at the level of syntactic clauses (Van Atteveldt et al, 2017). The main disadvantage of preserving positions is that it is very memory inefficient, especially if all tokens are kept and annotations are added.…”

Метод Контент-Аналізу Семантичної Частки В Текстах З Ознаками Психолінгвістичного Впливу

“…Існуючі методи контент-аналізу, що базуються на дослідженні граматичних та синтаксичних конструкцій [6][7][8] спеціалізуються на пошуку певних слів-маркерів, ключових фраз, синтаксичних конструкцій, однак цього не досить для проведення контекстуального дослідження та дослідження семантичного ядра і семантичної частки в умовах квантово-семантичного психолінгвістичного аналізу. При цьому, сучасні методи семантичного контентаналізу [9][10] не розглядають семантику з точки зору квантово-семантичного аналізу, що є критичним в проведенні контент аналізу семантичної частки.…”