Predicción de valores léxico-afectivos para un conjunto de emociones complejas mediante análisis de semántica distribucional

Abstract

La semántica distribucional desarrolla métodos y técnicas para atribuir significado a las palabras por medio de las cuales estudia las propiedades distribucionales de grandes muestras de datos lexicales. Complementariamente, la información léxico-afectiva, representada usualmente por las dimensiones valencia y activación, se deriva del uso social de un término y, por tanto, puede ser inferida mediante el estudio de los contextos en los cuales aparece dicho término. En este trabajo se pone en consideración la utilidad de un método de estimación computacional de valores léxico-afectivos mediante la semántica distribucional para el idioma español. A través de la adaptación española del ANEW1 , se realizaron dos procedimientos. Por un lado, se comparó el método computacional de obtención de los valores de valencia y arousal, mediante regresiones lineales contra un modelo basado en redes neuronales que demostró el mejor ajuste de este último. Y por otro, se estimaron los valores léxico-afectivos para un conjunto de emociones complejas, para el que se comparó tal estimación, computacionalmente calculada con datos empíricos extraídos de otra comunidad lingüística (versión argentina), diferente a la cual dio origen a los datos con los cuales se entrenó el modelo (versión española). Entre estas estimaciones computacionales y los datos empíricamente derivados se encontraron correlaciones comparables a las halladas entre diferentes grupos etarios, géneros o regiones geográficas. Estos resultados dan cuenta de una llamativa base común de la lengua que permite una exploración de la carga afectiva de las palabras mediante semántica distribucional.

The tradition of dimensional models in the study of emotions suggests that affective space is better defined by a small number of non-specific general dimensions. This dimensional perspective in the study of emotions postulates that the minimal entities of representation are dimensions such as valence (attraction vs. rejection) and arousal (level of activation). Data collection in this perspective is done through the laborious process of resorting to the estimates of hundreds of people who must decide on a continuum of two dimensions: how positive or negative the object to which the concept alludes is, and what level of arousal it generates. To do so, generally, an image-based questionnaire developed to measure an emotional response is used, called SAM (Self Assessment Manikin), which is a set of synthesized drawings that can be used to guide the participants' response. As can be noted, the volume and quality of the procedures used to study these affective variables associated with concepts involves an arduous process of data collection and processing. The complexity of this work, due to the enormous amount and type of data, makes computational intelligence a very useful and novel tool for its approach in order to obtain reliable and reproducible results. Processing by means of distributional semantics obtains the meaning of a word by locating the context in which it appears through an intelligent search in large volumes of electronically stored data. Lexical-affective information, represented by the valence and activation dimensions, is a type of information that seems to be represented by the social use of a term and, therefore, it is plausible to infer it by studying the contexts in which the term appears. In this paper we consider the plausibility of the application of the method of estimating lexical-affective values by means of distributional semantics for the Spanish language. In order to achieve this objective, the Spanish adaptation of the ANEW is used for this purpose and, two procedures were carried out. On the one hand, the most traditionally used computational method of estimation by means of linear regressions was compared with a model based on neural networks, which showed the better fit of the latter. On the other hand, lexical-affective values were estimated for a set of complex emotions and, in order to verify the strength of the results, such estimation was compared with empirical data taken and processed in a linguistic community (Argentine), different from the community that gave rise to the data with which the computational model was trained (Spanish). The results have been very encouraging since, between the computationally derived estimates and the empirically derived data with the Argentine population, correlations were found to be sufficiently strong and comparable to those that can be found when the same comparison is made between empirically derived results with different age groups, or between different genders, or when comparing different geographical regions. These results point to a striking common base of the language, a basic common core of concepts, which can be explored by means of the procedures and techniques of distributional semantics.