Sentiment analysis is a relevant area in the natural language processing context–(NLP) that allows extracting opinions about different topics such as customer service and political elections. Sentiment analysis is usually carried out through supervised learning approaches and using labeled data. However, obtaining such labels is generally expensive or even infeasible. The above problems can be faced by using models based on self-supervised learning, which aims to deal with various machine learning paradigms in the absence of labels. Accordingly, we propose a self-supervised approach for sentiment analysis in Spanish that comprises a lexicon-based method and a supervised classifier. We test our proposal over three corpora; the first two are labeled datasets, namely, CorpusCine and PaperReviews. Further, we use an unlabeled corpus conformed by news related to the Colombian conflict to understand the university journalistic narrative of the war in Colombia. Obtained results demonstrate that our proposal can deal with sentiment analysis settings in scenarios with unlabeled corpus; in fact, it acquires competitive performance compared with state-of-the-art techniques in partially-labeled datasets.

Este artículo es un acercamiento a la dinámica y al cambio que se presenta en el discurso político a raíz de la aparición de un nuevo concepto: el discurso mediado por ordenadores, el cual surgió gracias al avance tecnológico y a la aparición de la web 2.0. El presente estudio analiza la construcción semántica y sintáctica de los mensajes publicados en la red social digital twitter del presidente de la república de Colombia, Juan Manuel Santos Calderón y del ex presidente Álvaro Uribe Vélez, quienes se han caracterizado por mostrar una enemistad debido a sus diferencias ideológicas. El proyecto incluye métodos digitalizados de investigación como los análisis de contenido mediados por ordenador y el diseño de representaciones visuales o cartográficas de las dinámicas que se dan en la herramienta de microblogging, las cuales permiten observar las comunidades de discusión en torno a estos dos políticos y el impacto que generan con su estilo discursivo.

Since their early stages, developing narratives has been characteristic of human beings, allowing them to create community and generate cohesion—one that has endured for thousands of years is “peace”. However, in some territories, excessive ambition, fear imposed by force, and power over laws have proliferated. In the case of Colombia, war as an industry empowers different sides that are either endorsed or rendered invisible in the narratives of traditional mass media. Media content has always favored war journalism and neglected two vital approaches: peace journalism (PP) and university journalism. This study’s relevance lies in its use of big data, automated lexicometry, and statistical discourse analysis to understand how university journalism built a peace journalism agenda, taking the narrative of the Peace Agreement in Colombia as a framework of observation, with a clear result in the importance of equity, diversity, and equality in a peaceful transition scenario in Colombia. The study reveals that university journalism has a diverse narrative approach, focusing on presenting the social problems and inequities, the lack of political capacities within communities, the need for a transitional approach toward peace, and the pursuit of truth. The study used mixed research techniques where students narrated their individual perspectives that informed a collective view by integrating the voices of those who suffer the conflict daily. Simultaneously, they showed how academia, from its training function, develops exercises that may compromise the integrity of the axiological values of communication and journalism. The main implication of our study suggests the need to strengthen pedagogical processes of peace in the curriculum and training that enable the next generation of journalists in the country to potentially shift their discourse toward peace journalism and divergent solutions, as opposed to those proposed by traditional media. In conclusion, including youth opinions that were supported by experts on the process introduced an element of community empowerment and recognition of victims within the context and social structure of the Colombian conflict.

Internet como herramienta transformadora de las relaciones familiares entre adultos mayores y sus familiares migrantes.

El presente artículo estudia la relación entre herramientas tecnológicas y comunicación en salud, con el fin de comprender cómo los jóvenes utilizan los dispositivos digitales y revisar la efectividad que tendrían estos espacios para disminuir el consumo de tabaco. El trabajo utilizó un método mixto de encuestas, grupos focales y fotografía participativa, que permitió comprender cómo las redes sociales se han convertido en un espacio público digital juvenil y por consiguiente, una herramienta útil para transmitir campañas de promoción y prevención en temas de salud y políticas públicas. Los jóvenes se ven enfrentados a múltiples espacios de representación, visibilización e intercambio en línea, llevando a los jóvenes a evaluar su rol como ciudadanos digitales en múltiples ciberespacios, es por esta razón que las campañas de comunicación colaborativa y transmedia pueden ser la solución para disminuir la percepción positiva hacia el tabaco y la repetición de pares.