ABSTRACT Despite the remarkable success of language models, they still encounter difficulties in accurately performing tasks related to morality intelligence. Moral values vary across cultures and contexts, and are highly subjective. This work focuses on evaluating the ability of transformer models to assess morality in text by exploiting their capacity to understand and leverage context through attention mechanisms. Additionally, we propose a new taxonomy to organize existing research and structure future studies in this field. Firstly, we evaluate the performance of moral value detection at different levels of complexity by evaluating the F1‐score. Furthermore, this work develops an exhaustive analysis of the impact of incorporating subjective word embeddings, drawing on lexical resources that reflect both emotional and moral dimensions. Finally, we examine the variance in performance metrics to evaluate the impact on the model generalization ability when applied to different domains, using a cross‐dataset methodology. Experimental results show that adding lexical information positively affects the model's ability to capture underlying moral values in text, and the observed improvements demonstrate the effectiveness of integrating enriched data and subjective perspectives to enhance model robustness.

Canceling is a morally-driven phenomenon that hinders the development of safe social media platforms and contributes to ideological polarization.To address this issue we present the Canceling Attitudes Detection (CADE) dataset, an annotated corpus of canceling incidents aimed at exploring the factors of disagreements in evaluating people's canceling attitudes on social media.Specifically, we study the impact of annotators' morality in their perception of canceling, showing that morality is an independent axis for the explanation of disagreement on this phenomenon.Annotator's judgments heavily depend on the type of controversial events and involved celebrities.This shows the need to develop more event-centric datasets to better understand how harms are perpetrated in social media and to develop more aware technologies for their detection.WARNING: the CADE corpus could contain racist, sexist, violent, and generally offensive content.

Enrico Liscio, Oscar Araque, Lorenzo Gatti, Ionut Constantinescu, Catholijn Jonker, Kyriaki Kalimeri, Pradeep Kumar Murukannaiah. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Several lexica for sentiment analysis have been developed; while most of these come with word polarity annotations (e.g., positive/negative), attempts at building lexica for finer-grained emotion analysis (e.g., happiness, sadness) have recently attracted significant attention. They are often exploited as a building block for developing emotion recognition learning models, and/or used as baselines to which the performance of the models can be compared. In this work, we contribute two new resources, that we call DepecheMood++ (DM++): a) an extension of an existing and widely used emotion lexicon for English; and b) a novel version of the lexicon, targeting Italian. Furthermore, we show how simple techniques can be used, both in supervised and unsupervised experimental settings, to boost performance on datasets and tasks of varying degree of domain-specificity. Also, we report an extensive comparative analysis against other available emotion lexica and state-of-the-art supervised approaches, showing that DepecheMood++ emerges as the best-performing non-domain-specific lexicon in unsupervised settings. We also observe that simple learning models on top of DM++ can provide more challenging baselines. We finally introduce embedding-based methodologies to perform a) vocabulary expansion to address data scarcity and b) vocabulary porting to new languages in case training data is not available.

The Internet has become an effective tool for terrorist and radical groups to spread their propaganda. One of the current problems is to detect these radical messages in order to block them or promote counter-narratives.In this work, we propose the use of stylometric methods for characterizing radical messages. We have used a machine learning approach to classify radical texts based on a corpus of news from radical sources such as the so-called ISIS online magazines Dabiq and Rumiyah, as well as news from general newspapers. The results show that stylometric features are effective for radical text classification.

Lexical resources are widely popular in the field of Sentiment Analysis, as they represent a resource that directly encodes sentimental knowledge. Usually sentiment lexica are used for polarity estimation through the matching of words contained in a text and their associated lexicon sentiment polarities. Nevertheless, such resources have limitations in vocabulary coverage and domain adaptation. Besides, many recent techniques exploit the concept of distributed semantics, normally through word embeddings. In this work, a semantic similarity metric is computed between text words and lexica vocabulary. Using this metric, this paper proposes a sentiment classification model that uses the semantic similarity measure in combination with embedding representations. In order to assess the effectiveness of this model, we perform an extensive evaluation. Experiments show that the proposed method can improve Sentiment Analysis performance over a strong baseline, being this improvement statistically significant. Finally, some characteristics of the proposed technique are studied, showing that the selection of lexicon words has an effect in cross-dataset performance.

Deep learning techniques for Sentiment Analysis have become very popular. They provide automatic feature extraction and both richer representation capabilities and better performance than traditional feature based techniques (i.e., surface methods). Traditional surface approaches are based on complex manually extracted features, and this extraction process is a fundamental question in feature driven methods. These long-established approaches can yield strong baselines, and their predictive capabilities can be used in conjunction with the arising deep learning methods. In this paper we seek to improve the performance of deep learning techniques integrating them with traditional surface approaches based on manually extracted features. The contributions of this paper are sixfold. First, we develop a deep learning based sentiment classifier using a word embeddings model and a linear machine learning algorithm. This classifier serves as a baseline to compare to subsequent results. Second, we propose two ensemble techniques which aggregate our baseline classifier with other surface classifiers widely used in Sentiment Analysis. Third, we also propose two models for combining both surface and deep features to merge information from several sources. Fourth, we introduce a taxonomy for classifying the different models found in the literature, as well as the ones we propose. Fifth, we conduct several experiments to compare the performance of these models with the deep learning baseline. For this, we use seven public datasets that were extracted from the microblogging and movie reviews domain. Finally, as a result, a statistical study confirms that the performance of these proposed models surpasses that of our original baseline on F1-Score.

Sentiment and emotion analysis technologies have quickly gained momentum in industry and academia. This popularity has spawned a myriad of service and tools. Due to the lack of common interfaces and models, each of these services imposes specific interfaces and representation models. Heterogeneity makes it costly to integrate different services, evaluate them or switch between them. This work aims to remedy heterogeneity by providing an extensible framework and an API aligned with the NIF service specification. It also includes a reference implementation, a first step towards a successful and cost-effective adoption. The specific contributions in this paper are: (i) the Senpy framework, (ii) an architecture for the framework that follows a plug-in approach, (iii) a reference open source implementation of the architecture, (iv) the use and validation of the framework and architecture in a big data sentiment analysis European project. Our aim is to foster the development of a new generation of emotion aware services by isolating the development of new algorithms from the representation of results and the deployment of services.