Automatic Coherence Profile in Public Speeches of Three Latin American Heads-of-State

Different studies provide evidence that the computational psycholinguistic algorithm called Latent Semantic Analysis (LSA) allows measuring local and global coherence in texts similarly to human evaluation (Foltz, Kintsch, Landauer 1998; McNamara, Cai & Louwerse 2007; McCarthy, Briner, Rus, & McNamara, 2007; McNamara, Louwerse & Jeuniaux 2009; Louwerse, McCarthy & Graesser 2010). The texts used in all these studies are written in English and correspond to scientific and literary texts. In Spanish, there are some studies using LSA that measure the semantic similarity between texts in automatic summary assessment (Pérez, Alfonseca, Rodríguez, Gliozzo, Strapparava & Magnini 2005; León, Olmos, Escudero, Cañas & Salmerón 2006; Venegas 2007, 2009, 2011); however, automatic measurement of coherence in Spanish has not yet been sufficiently investigated. The present study aimed at identifying a global and local coherence profile in a corpus of speeches in Spanish of three Latin American Heads of States (Perón, Castro and Pinochet), using Latent Semantic Analysis. Local coherence is calculated through the measurement of implicit semantic similarity between adjacent sentences and global coherence through the measurement of the similarity among the semantic content of the paragraphs. The corpus under analysis corresponds to a sample of 107 speeches. The semantic space was built using a multi register corpus and it is available through the “Interface for the measurement of lexical semantic similarity” in the El Grial interface (www.elgrial.cl). Results showed a systematic difference between the speeches of the Heads of State in terms of both local and global coherence. The Bonferroni analysis established an effect that distinguishes Perón’s speeches from Pinochet’s and Castro’s speeches. This results show that Perón’s speeches are more topically related than the other leaders’, probably due to a discourse strategy to persuade voters. The identification of a profile of coherence might be relevant to predict cues of government discourse styles. Introduction Cohesion and coherence are two main features in discourse comprehension and production. Cohesion is defined as "the use of explicit linguistic devices to signal relations between sentences and parts of texts" (Connor 1996:83). These cohesive devices are words or phrases that help the reader associate previous propositions with subsequent ones. Halliday and Hasan (1976) established that cohesion refers to the range of possibilities that exist for linking something with what has gone before, i.e. a meaning relation. There is always a possibility that a text be cohesive without necessarily being coherent: cohesion does not guarantee coherence: “cohesion is determined by lexically and grammatically overt intersentential relationships, whereas coherence is based on semantic relationships" (Connor 1996:83). Coherence then refers to how a text is organized, how the ideas are developed, and how the contents are related. In sum, coherent texts make sense to the reader. Despite the possible controversy in the conceptualization of both terms (Sanders & Pander 2006), in the present study we conceptualized coherence as a representational relationship and cohesion as the textual indications that coherent representation should be built on (Louwerse 2004). More specifically, we focused in local and global coherence. Both local and global coherence are interesting to be studied in linguistic and psycholinguistic approaches to discourse (Sanders & Spooren 2009; Louwerse & Jeuniaux 2009). The measurement of coherence relations has been explored computationally using different techniques. This line of research has been supported by studies developed by researchers like Foltz, Kintsch, and Landauer (1998), McNamara, Cai, and Louwerse (2007), McCarthy, Briner, Rus, and McNamara (2007); McNamara, Louwerse, and Jeuniaux (2009), Louwerse, McCarthy, and Graesser Copyright © 201 , Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. 2 250 Proceedings of the Twenty-Fifth International Florida Artificial Intelligence Research Society Conference