Alfredo Garcia

Detecting sensitive information considering privacy is a relevant issue on Online Social Networks (OSNs). It is often difficult for users to manage the privacy associated with their posts on social networks taking into account all the possible consequences. The aim of this work is to provide information about the sensitivity of the content of a publication when a user is going to share it in OSN. For this purpose, we developed a privacy-assistant agent that detects sensitive information. Based on this information, the agent provides a message through a nudge mechanism warning about the possible risks of sharing the message. To avoid being annoying, the agent also considers the user’s previous behaviour (e.g. if he previously ignored certain nudges) and adapts the messages it sends to give more relevance to those categories that are more important to the user from the point of view of the privacy risk. This agent was integrated into the social network Pesedia. We analysed the performance of different models to detect a set of sensitive categories (i.e. location, medical, drug/alcohol, emotion, personal attacks, stereotyping, family and association details, personal details and personally identifiable information) in a dataset of tweets in Spanish. The model that obtained the best results (i.e. F1 and accuracy) and that was finally integrated into the privacy-assistant agent was transformer-based.

This paper offers a novel analysis of the Spanish light verbs poner ‘to become’ and quedar ‘to become/stay’ in combination with adjectives. These verbs have the peculiarity that they may appear with or without se in these constructions, with clear effects on argument structure and thematic and aspectual interpretation. I propose a unified formal analysis that takes event complexity and argument coindexing as the common denominator of se in these complex predicates. I further observe that these effects with se are not exclusive to these light verbs, but can also be observed in certain types of lexical verbs, strongly suggesting that both lexical and light verbs lexicalize the same eventive spine.

Resumen: El enfoque de máquinas nomológicas como esquema de funcionamiento de los modelos económicos supone la existencia de conjunciones constantes de eventos que tienen lugar en tanto se cumplan con determinadas cláusulasceteris paribus. Este enfoque supone causalidad del tipo lineal, una metodología del tipo macro-micro-macro, y un aislamiento respecto del entorno en el cual dicha máquina opera, lo cual lo hace congruente con el pensamiento neo-mecanicista. Consideramos que estos supuestos son cuestionables bajo el paradigma de la complejidad. En particular, dado que gran parte de los fenómenos económicos responden a una causalidad no lineal, es necesario tener en consideración interacciones que no se dan en un nivel ni micro ni macro sinomeso, y que no es necesario ni conveniente hacer un aislamiento con el entorno, sino que es posible contemplarlo utilizando modelos de simulación.: The nomological machines approach as a scheme of operation of economic models presupposes the existence of constant conjunctions of events that take place as long as certain ceteris paribus clauses are fulfilled. This approach involves linear causality, a macro-micro-macro methodology, and an isolated environment in which the machine operates, which makes it consistent with the neo-mechanistic approach. We believe that these assumptions are questionable under the paradigm of complexity. Given that a large part of economic phenomena responds to non-linear causality, it is necessary to consider interactions that do not occur at a micro or macro level but rather at a meso-level, and that it is neither necessary nor desirable to isolate from the environment, but it is possible to contemplate it using simulation models.