María Grandury, Javier Aula-Blasco, Júlia Falcão, Clémentine Fourrier, Miguel González Saiz, Gonzalo Martínez, Gonzalo Santamaria Gomez, Rodrigo Agerri, Nuria Aldama García, Luis Chiruzzo, Javier Conde, Helena Gomez Adorno, Marta Guerrero Nieto, Guido Ivetta, Natàlia López Fuertes, Flor Miriam Plaza-del-Arco, María-Teresa Martín-Valdivia, Helena Montoro Zamorano, Carmen Muñoz Sanz, Pedro Reviriego, Leire Rosado Plaza, Alejandro Vaca Serrano, Estrella Vallecillo-Rodríguez, Jorge Vallego, Irune Zubiaga. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

With mental health issues on the rise on the Web, especially among young people, there is a growing need for effective identification and intervention. In this paper, we introduce a new open-sourced corpus for the early detection of mental disorders in Spanish, focusing on eating disorders, depression, and anxiety. It consists of user messages posted on groups within the Telegram message platform and contains over 1,300 subjects with more than 45,000 messages posted in different public Telegram groups. This corpus has been manually annotated via crowdsourcing and is prepared for its use in several Natural Language Processing tasks including text classification and regression tasks. The samples in the corpus include both text and time data. To provide a benchmark for future research, we conduct experiments on text classification and regression by using state-of-the-art transformer-based models.

This paper describes the automated generation of CounterNarratives (CNs) for Hate Speech (HS) in Spanish using GPT-based models. Our primary objective is to evaluate the performance of these models in comparison to human capabilities. For this purpose, the English CONAN Multitarget corpus is taken as a starting point and we use the DeepL API to automatically translate into Spanish. Two GPT-based models, GPT-3 and GPT-4, are applied to the HS segment through a few-shot prompting strategy to generate a new CN. As a consequence of our research, we have created a high quality corpus in Spanish that includes the original HS-CN pairs translated into Spanish, in addition to the CNs generated automatically with the GPT models and that have been evaluated manually. The resulting CONAN-MT-SP corpus and its evaluation will be made available to the research community, representing the most extensive linguistic resource of CNs in Spanish to date. The results demonstrate that, although the effectiveness of GPT-4 outperforms GPT-3, both models can be used as systems to automatically generate CNs to combat the HS. Moreover, these models consistently outperform human performance in most instances.

Within textual emotion classification, the set of relevant labels depends on the domain and application scenario and might not be known at the time of model development. This conflicts with the classical paradigm of supervised learning in which the labels need to be predefined. A solution to obtain a model with a flexible set of labels is to use the paradigm of zero-shot learning as a natural language inference task, which in addition adds the advantage of not needing any labeled training data. This raises the question how to prompt a natural language inference model for zero-shot learning emotion classification. Options for prompt formulations include the emotion name anger alone or the statement “This text expresses anger”. With this paper, we analyze how sensitive a natural language inference-based zero-shot-learning classifier is to such changes to the prompt under consideration of the corpus: How carefully does the prompt need to be selected? We perform experiments on an established set of emotion datasets presenting different language registers according to different sources (tweets, events, blogs) with three natural language inference models and show that indeed the choice of a particular prompt formulation needs to fit to the corpus. We show that this challenge can be tackled with combinations of multiple prompts. Such ensemble is more robust across corpora than individual prompts and shows nearly the same performance as the individual best prompt for a particular corpus.

In this paper we present SHARE, a new lexical resource with 10,125 offensive terms and expressions collected from Spanish speakers. We retrieve this vocabulary using an existing chatbot developed to engage a conversation with users and collect insults via Telegram, named Fiero. This vocabulary has been manually labeled by five annotators obtaining a kappa coefficient agreement of 78.8%. In addition, we leverage the lexicon to release the first corpus in Spanish for offensive span identification research named OffendES_spans. Finally, we show the utility of our resource as an interpretability tool to explain why a comment may be considered offensive.

BACKGROUND: Natural language processing (NLP) and text mining technologies for the extraction and indexing of chemical and drug entities are key to improving the access and integration of information from unstructured data such as biomedical literature. METHODS: In this paper we evaluate two important tasks in NLP: the named entity recognition (NER) and Entity indexing using the SNOMED-CT terminology. For this purpose, we propose a combination of word embeddings in order to improve the results obtained in the PharmaCoNER challenge. RESULTS: For the NER task we present a neural network composed of BiLSTM with a CRF sequential layer where different word embeddings are combined as an input to the architecture. A hybrid method combining supervised and unsupervised models is used for the concept indexing task. In the supervised model, we use the training set to find previously trained concepts, and the unsupervised model is based on a 6-step architecture. This architecture uses a dictionary of synonyms and the Levenshtein distance to assign the correct SNOMED-CT code. CONCLUSION: On the one hand, the combination of word embeddings helps to improve the recognition of chemicals and drugs in the biomedical literature. We achieved results of 91.41% for precision, 90.14% for recall, and 90.77% for F1-score using micro-averaging. On the other hand, our indexing system achieves a 92.67% F1-score, 92.44% for recall, and 92.91% for precision. With these results in a final ranking, we would be in the first position.

Abstract Accurate negation identification is one of the most important tasks in the context of sentiment analysis. In order to correctly interpret the sentiment value of a particular expression, we need to identify whether it is in the scope of negation. While much of the work on negation detection has focused on English, we have seen recent developments that provide accurate identification of negation in other languages. In this paper, we provide an overview of negation detection systems and describe an implementation of a Spanish system for negation cue detection and scope identification. We apply this system to the sentiment analysis task, confirming also for Spanish that improvements can be gained from accurate negation detection. The paper contributes an implementation of negation detection for sentiment analysis in Spanish and a detailed error analysis. This is the first work in Spanish in which a machine learning negation processing system is applied to the sentiment analysis task. Existing methods have used negation rules that have not been assessed, perhaps because the first Spanish corpus annotated with negation for sentiment analysis has only recently become available.

In recent years emotion detection in text has become more popular due to its potential applications in fields such as psychology, marketing, political science, and artificial intelligence, among others. While opinion mining is a well-established task with many standard data sets and well-defined methodologies, emotion mining has received less attention due to its complexity. In particular, the annotated gold standard resources available are not enough. In order to address this shortage, we present a multilingual emotion data set based on different events that took place in April 2019. We collected tweets from the Twitter platform. Then one of seven emotions, six Ekman’s basic emotions plus the “neutral or other emotions”, was labeled on each tweet by 3 Amazon MTurkers. A total of 8,409 in Spanish and 7,303 in English were labeled. In addition, each tweet was also labeled as offensive or no offensive. We report some linguistic statistics about the data set in order to observe the difference between English and Spanish speakers when they express emotions related to the same events. Moreover, in order to validate the effectiveness of the data set, we also propose a machine learning approach for automatically detecting emotions in tweets for both languages, English and Spanish.

In this work we address the processing of negation in Spanish. We first present a machine learning system that processes negation in Spanish. Specifically, we focus on two tasks: i) negation cue detection and ii) scope identification. The corpus used in the experimental framework is the SFU Corpus. The results for cue detection outperform state-of-the-art results, whereas for scope detection this is the first system that performs the task for Spanish. Moreover, we provide a qualitative error analysis aimed at understanding the limitations of the system and showing which negation cues and scopes are straightforward to predict automatically, and which ones are challenging.

Negation is a universal linguistic phenomenon with a great qualitative impact on natural language processing applications. The availability of corpora annotated with negation is essential to training negation processing systems. Currently, most corpora have been annotated for English, but the presence of languages other than English on the Internet, such as Chinese or Spanish, is greater every day. In this study, we present a review of the corpora annotated with negation information in several languages with the goal of evaluating what aspects of negation have been annotated and how compatible the corpora are. We conclude that it is very difficult to merge the existing corpora because we found differences in the annotation schemes used, and most importantly, in the annotation guidelines: the way in which each corpus was tokenized and the negation elements that have been annotated. Differently than for other well established tasks like semantic role labeling or parsing, for negation there is no standard annotation scheme nor guidelines, which hampers progress in its treatment.

Today, misogyny and xenophobia are some of the most important social problems. With the increase in the use of social media, this feeling of hatred toward women and immigrants can be more easily expressed, and therefore it can have harmful effects on social media users. For this reason, it is important to develop systems capable of detecting hateful comments automatically. In this article, we analyze the hate speech in Spanish tweets against women and immigrants conducting classification experiments using different approaches. Moreover, we create appropriate language resources for hate speech detection in Spanish.

Polarity classification is a well-known Sentiment Analysis task. However, most research has been oriented towards developing supervised or unsupervised systems without paying much attention to certain linguistic phenomena such as negation. In this paper we focus on this specific issue in order to demonstrate that dealing with negation can improve the final system. Although we can find some studies of negation detection, most of them deal with English documents. On the contrary, our study is focused on the scope of negation in Spanish Sentiment Analysis. Thus, we have built an unsupervised polarity classification system based on integrating external knowledge. In order to evaluate the influence of negation we have implemented a specific module for negation detection by applying several rules. The system has been tested considering and without considering negation, using a corpus of tweets written in Spanish. The results obtained reveal that the treatment of negation can greatly improve the accuracy of the final system. Moreover, we have carried out a comprehensive statistical study in order to demonstrate our approach. To the best of our knowledge, this is the first work which statistically demonstrates that taking into account negation significantly improves the polarity classification of Spanish tweets.

The availability of corpora annotated with negation information is essential to develop negation processing systems in any language. However, there is a lack of these corpora even for languages like English, and when there are corpora available they are small and the annotations are not always compatible across corpora. In this paper we review the existing corpora annotated with negation in Spanish with the purpose of first, gathering the information to make it available for other researchers and, second, analyzing how compatible are the corpora and how has the linguistic phenomenon been addressed. Our final aim is to develop a supervised negation processing system for Spanish, for which we need training and test data. Our analysis shows that it will not be possible to merge the small corpora existing for Spanish due to lack of compatibility in the annotations.

Salud M. Jiménez Zafra, Giacomo Berardi, Andrea Esuli, Diego Marcheggiani, María Teresa Martín-Valdivia, Alejandro Moreo Fernández. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015.

Until now, most of the methods published for polarity classification in Twitter have used a supervised approach. The differences between them are only the features selected and the method used for weighting them. In this article, we present an unsupervised method for polarity classification in Twitter. The method is based on the expansion of the concepts expressed in the tweets through the application of PageRank to WordNet. In addition, we integrate SentiWordNet to compute the final value of polarity. The synsets values are weighted with the PageRank scores obtained in the previous random walk process over WordNet. The results obtained show that disambiguation and expansion are good strategies for improving overall performance.

Abstract In recent years, the interest among the research community in sentiment analysis (SA) has grown exponentially. It is only necessary to see the number of scientific publications and forums or related conferences to understand that this is a field with great prospects for the future. On the other hand, the Twitter boom has boosted investigation in this area due fundamentally to its potential applications in areas such as business or government intelligence, recommender systems, graphical interfaces and virtual assistance. However, to fully understand this issue, a profound revision of the state of the art is first necessary. It is for this reason that this paper aims to represent a starting point for those investigations concerned with the latest references to Twitter in SA.

Polarity classification is one of the main tasks related to the opinion mining and sentiment analysis fields. The aim of this task is to classify opinions as positive or negative. There are two main approaches to carrying out polarity classification: machine learning and semantic orientation based on the integration of knowledge resources. In this study, we propose to combine both approaches using a voting system based on the majority rule. In this way, we attempt to improve the polarity classification of two parallel corpora such as the opinion corpus for Arabic (OCA) and the English version of the OCA (EVOCA). Several experiments have been performed to check the feasibility of the proposed method. The results show that the experiment that took into account both approaches in the voting system obtained the best performance. Moreover, it is also shown that the proposed method slightly improves the best results obtained using machine learning approaches solely over the OCA and the EVOCA separately. Therefore, we can conclude that the approach proposed here might be considered a good strategy for polarity detection when we work with bilingual parallel corpora.

Abstract Sentiment analysis is a challenging new task related to text mining and natural language processing. Although there are, at present, several studies related to this theme, most of these focus mainly on English texts. The resources available for opinion mining (OM) in other languages are still limited. In this article, we present a new Arabic corpus for the OM task that has been made available to the scientific community for research purposes. The corpus contains 500 movie reviews collected from different web pages and blogs in Arabic, 250 of them considered as positive reviews, and the other 250 as negative opinions. Furthermore, different experiments have been carried out on this corpus, using machine learning algorithms such as support vector machines and Nave Bayes. The results obtained are very promising and we are encouraged to continue this line of research.