In emergency situations users of social networks convey all sorts of what have been called communicative intentions, well-known since the work of Austin (1962) and Searle (1969) as speech acts (SA). ...While speech acts have been the focus of close scrutiny in the philosophical and linguistic literature (see (Portner, 2018) for extended discussion), their role has been only rarely understood and exploited in processing social media content about crisis events, our focus here. Current work on communicative intentions in social media are topic-oriented, focusing on the correlation between SA and specific topics such as crisis (e.g., earthquakes) but also politics, celebrities, cooking, travel, etc. It has been observed that people globally tend to react to natural disasters with SA distinct from those used in other contexts (e.g., celebrities, which are essentially made up of comments). Here, we explore the further hypothesis of a correlation between different SA types and urgency and propose an in depth linguistic and computational analysis of communicative intentions in tweets from an urgency-oriented perspective. Indeed, SA are mostly relevant to identify intentions, desires, plans and preferences towards action and to ultimately produce a system intended to help rescue teams. Our contribution is four-fold and consists of: (1) A two-layer annotation scheme of speech acts both at the tweet and sub-tweet levels, (2) A new French dataset of about 13K tweets annotated for both urgency and SA, targeting both expected (e.g., storms) and unexpected or sudden (e.g., building collapse, explosion) events, (3) A thorough analysis of the annotations studying in particular the correlation between SA and the urgency of the message, SA and intentions to act categories (e.g., human damages), and SA and crisis types, finally, (4) A set of deep learning experiments to detect SA in crises related corpora. Our results show a strong correlation between SA and urgency annotations at both the tweet and sub-tweet levels with a particular salient correlation in the latter case, which constitutes a first important step towards SA-aware NLP-based crisis management on social media.
Automated medical coding, an essential task for healthcare operation and delivery, makes unstructured data manageable by predicting medical codes from clinical documents. Recent advances in deep ...learning and natural language processing have been widely applied to this task. However, deep learning-based medical coding lacks a unified view of the design of neural network architectures. This review proposes a unified framework to provide a general understanding of the building blocks of medical coding models and summarizes recent advanced models under the proposed framework. Our unified framework decomposes medical coding into four main components, i.e., encoder modules for text feature extraction, mechanisms for building deep encoder architectures, decoder modules for transforming hidden representations into medical codes, and the usage of auxiliary information. Finally, we introduce the benchmarks and real-world usage and discuss key research challenges and future directions.
languages, both on the source and target sides, with a single translation engine. In this paper, we present the general principles underlying these systems and the innovations that have made them ...possible, before discussing their main strengths and weaknesses.
Les systèmes de traduction automatique (TA) neuronale ont fait ces dernières années des progrès tangibles, qui les ont rendus utilisables pour un nombre croissant de domaines et de couples de langues. Les systèmes neuronaux reposent sur des algorithmes d’apprentissage automatique et leur développement nécessite de grands corpus électroniques de textes parallèles, alignés au niveau des phrases, des ressources qui n’existent que pour un petit nombre de couples de langues et de domaines. Pour pallier ce manque, une proposition récente consiste à développer des systèmes de traduction dits « multilingues ». Ces développements ont été impulsés en particulier par les grands acteurs de l’Internet, pour qui le traitement d’un maximum de langues est un enjeu majeur. La principale caractéristique de ces architectures est de pouvoir traiter, avec un unique système de traduction, de multiples langues, aussi bien du côté source que du côté cible. Dans cette contribution, nous exposons les principes généraux qui sous-tendent ces systèmes et les innovations qui les ont rendus possibles, avant d’en discuter les principales forces et faiblesses.
The rate of plagiarism and false content in scientific literature varies depending on the field of study and the methods used to detect it. According to some studies, the overall rate of plagiarism ...in scientific literature is estimated to be around 2-3% 1. However, the rate can be higher in certain fields and for certain types of content. Additionally, the rate of false or fraudulent content in scientific literature is difficult to quantify, as it often goes undetected or is not reported. However, cases of scientific misconduct, including the fabrication and falsification of data, have been reported in various fields and can have serious consequences for both the authors and the scientific community. It is important for the scientific community to maintain high standards of ethics and accuracy in scientific research to ensure the validity and reliability of the published literature. In this editorial, we will touch upon the description of Large Language Models, define their limits and strengths and finally explore options to detect fraudulent manuscripts. Large Language Models (LLM) have the potential to assist researchers in generating clear and concise writing, summarising vast amounts of information and performing various language-related tasks 2. This can potentially save * Matthieu Ollivier
The purpose of this study was to test a hypothesized model that specified direct and indirect linkages between the individual difference variables of epistemic beliefs, need for cognition, individual ...interest, and prior knowledge, the processing variables of effort, deeper-level strategies, and situational interest, and multiple-text comprehension. Using a path analysis approach with a sample of 279 Norwegian upper secondary school students, results indicated that students' effort and deeper-level strategies predicted their multiple-text comprehension, with the individual difference variables indirectly affecting multiple-text comprehension through their influence on effortful, adaptive multiple-text processing. In addition, students' prior knowledge about the topic of the texts seemed to affect their multiple-text comprehension directly as well as indirectly. Both theoretical and educational implications of the results are discussed.
•Path analysis revealed direct and indirect effects on multiple-text comprehension.•Effort and deeper-level strategies had direct effects on comprehension.•Epistemic beliefs, need for cognition, interest and knowledge had indirect effects.
•A novel method for predicting stock price movement was presented.•Topics and sentiments of them were extracted from social media as the feature.•Two methods were proposed to capture the ...topic-sentiment feature.•Integration of the sentiments was investigated via a large scale experiment.•Our model outperformed other methods in the average accuracy of 18 stocks.
The goal of this research is to build a model to predict stock price movement using the sentiment from social media. Unlike previous approaches where the overall moods or sentiments are considered, the sentiments of the specific topics of the company are incorporated into the stock prediction model. Topics and related sentiments are automatically extracted from the texts in a message board by using our proposed method as well as existing topic models. In addition, this paper shows an evaluation of the effectiveness of the sentiment analysis in the stock prediction task via a large scale experiment. Comparing the accuracy average over 18 stocks in one year transaction, our method achieved 2.07% better performance than the model using historical prices only. Furthermore, when comparing the methods only for the stocks that are difficult to predict, our method achieved 9.83% better accuracy than historical price method, and 3.03% better than human sentiment method.
Text processing tasks commonly grapple with the challenge of high dimensionality. One of the most effective solutions to this challenge is to preprocess text data through feature selection methods. ...Feature selection can select the most advantageous features for subsequent operations (e.g., classification) from the native feature space of the text. This process effectively trims the feature space’s dimensionality, enhancing subsequent operations’ efficiency and accuracy. This paper proposes a straightforward and efficient filter feature selection method based on document-term matrix unitization (DTMU) for text processing. Diverging from previous filter feature selection methods that concentrate on scoring criteria definition, our method achieves more optimal feature selection by unitizing each column of the document-term matrix. This approach mitigates feature-to-feature influence and reinforces the role of the weighting proportion within the features. Subsequently, our scoring criterion subtracts the sum of weights for negative samples from positive samples and takes the absolute value. We conduct numerical experiments to compare DTMU with four advanced filter feature selection methods: max–min ratio metric, proportional rough feature selector, least loss, and relative discrimination criterion, along with two classical filter feature selection methods: Chi-square and information gain. The experiments are performed on four ten-thousand-dimensional feature space datasets: book, dvd, music, movie and two thousand-dimensional feature space datasets: imdb, amazon_cells, sourced from Amazon product reviews and movie reviews. Experimental findings demonstrate that DTMU selects more advantageous features for subsequent operations and achieves a higher dimensionality reduction rate than those of the other six methods used for comparison. Moreover, DTMU exhibits robust generalization capabilities across various classifiers and dimensional datasets. Notably, the average CPU time for a single run of DTMU is measured at 1.455 s.
•This paper offers DTMU, a filter feature selection method enhancing feature quality via unitization for improved properties.•DTMU is notably user-friendly, involving only two straightforward steps.•This paper substantiates, through numerical experiments, that DTMU stands as an advanced and effective method.