Browsing by Subject "Sentiment analysis"

Now showing 1 - 12 of 12
  • Thumbnail Image
    Publication
    Open Access
    A study on LIWC categories for opinion mining in Spanish reviews
    (SAGE Publications, 2014-08-26) Salas Zárate, María del Pilar; López López, Estanislao; Valencia García, Rafael; Aussenac Gilles, Natalie; Almela, Ángela; Alor Hernández, Giner; Filología Inglesa
    With the exponential growth of social media, that is, blogs and social networks, organizations and individual persons are increasingly using the number of reviews of these media for decision-making about a product or service. Opinion mining detects whether the emotions of an opinion expressed by a user on Web platforms in natural language are positive or negative. This paper presents extensive experiments to study the effectiveness of the classification of Spanish opinions in five categories: highly positive, highly negative, positive, negative and neutral, using the combination of the psychological and linguistic features of LIWC (Linguistic Inquiry and Word Count). LIWC is a text analysis software that enables the extraction of different psychological and linguistic features from natural language text. For this study, two corpora have been used, one about movies and one about technological products. Furthermore, we conducted a comparative assessment of the performance of various classification techniques, J48, SMO and BayesNet, using precision, recall and F-measure metrics. The findings revealed that the positive and negative categories provide better results than the other categories. Finally, experiments on both corpora indicated that SMO produces better results than BayesNet and J48 algorithms, obtaining an F-measure of 90.4 and 87.2% in each domain.
  • Thumbnail Image
    Publication
    Open Access
    Dividend announcement and the value of sentiment analysis
    (Taylor & Francis Group, 2024-02-26) Álvarez Díez, Susana; Baixauli Soler, Juan Samuel; Kondratenko, Anna; Lozano Reina, Gabriel; Organización de Empresas y Finanzas; Facultades, Departamentos, Servicios y Escuelas::Departamentos de la UMU::Organización de Empresas y Finanzas
    Payout policy constitutes one of the most important corporate financial decisions since dividends are essential factors in determining a firm’s value. A dividend announcement generates a market signal which translates into changes in stock returns, impacting short-term price fluctuations and producing abnormal returns. The sample consists of 394 companies listed on the S&P500 index, from which 1574 dividend announcements and 7222 news items are derived during the years 2022–2023. News pieces are obtained from 58 specialized sources, and ChatGPT is used to automate the sentiment extracted from them. Using sentiment analysis, this paper shows the key role played by sentiments derived from financial news posted just after dividend announcements in predicting market reaction and helping investors to select optimal investment strategies. This paper contributes to the current literature, highlighting the influence that sentiments have on determining stock market returns.
  • Thumbnail Image
    Publication
    Open Access
    Un estudio traductológico del sentimiento en los informes financieros español/inglés: las emociones en la economía desde la perspectiva del Análisis del Sentimiento y la Teoría de la Valoración
    (Universidad de Granada, 2020-10-27) Orts Llopis, María Ángeles; Traducción e Interpretación
    Esta investigación explora el léxico emocional en un corpus paralelo de informes financie­ros en español y su traducción al inglés. En primer lugar, se realizó una revisión general de las frecuencias léxicas, seguida de un procesamiento del corpus con el software Lingmotif de Análisis del Sentimiento (SA) para diagnosticar la intensidad y polaridad emotiva en los textos. Finalmente, los ítems cargados de emoción de ambas versiones se clasificaron dentro del marco de la Teoría de la Valoración (AT), con el fin de catalogar con mayor precisión los elementos de polaridad positiva y negativa. En general, nuestros resultados muestran cómo la intensidad y polaridad de los sentimientos se conservan generalmente tanto en el TO como en TM, mientras que la forma en que se expresan varía de una versión a otra por razones funcionales. -------------------------
  • Thumbnail Image
    Publication
    Open Access
    Evaluación de la satisfacción del cliente en hoteles de Gran Caribe del destino La Habana
    (Servicio de Publicaciones, Universidad de Murcia, 2026) Guerra Castellón, Emilio Enrique; Vázquez Alfonso, Yasser; Núñez Torres, Edgar; Sin departamento asociado
    Este estudio evalúa la satisfacción del cliente en hoteles del grupo Gran Caribe en el destino La Habana mediante un análisis de sentimiento aplicado a 57 884 opiniones obtenidas con web scraping de Trip Advisor, Booking, Expedia y la Central de Reservas. Se empleó la l ibrería Pysentimiento para calcular y clasificar el sentimiento. Mediante el diagrama de Pareto se identificaron los factores vitales que influyen en la satisfacción del cliente. El modelo multicriterio WASPAS permitió establecer un ranking de los hoteles, donde los mejores posicionados fueron Roc Presidente, NH Victoria y el Nacional de Cuba, destacados por emociones positivas, alto sentimiento promedio y baja dispersión. En contrast e, Neptuno- Tritón, Deauville y Plaza mostraron menor desempeño. El análisis confirma que las opiniones en l ínea son un indicador clave para monitorear la satisfacción y detectar áreas de mejora. Los resultados ofrecen insumos estratégicos para priorizar ac ciones que fortalezcan la competitividad de estos establecimientos
  • Thumbnail Image
    Publication
    Open Access
    Evaluation of transformer models for financial targeted sentiment analysis in Spanish
    (PeerJ, 2023-05-09) Pan, Ronghao; García Díaz, José Antonio; García Sánchez, Francisco; Valencia García, Rafael; Informática y Sistemas; Facultades de la UMU::Facultad de Informática
  • Thumbnail Image
    Publication
    Embargo
    Intraday stock prediction using sentiment analysis: evidence from dividend announcements
    (Taylor and Francis Group, Routledge, 2025-07-31) Álvarez-Diez, Susana; Baixauli Soler, J. Samuel; Kondratenko, Anna; Lozano Reina, Gabriel; Organización de Empresas y Finanzas
    This study explores whether sentiment extracted from financial news using large language models (LLMs) can predict abnormal intraday stock returns following dividend announcements. Drawing on 4,682 news items linked to 1,258 announcements from 394 S&P 500 companies (January 2023–January 2024), we use ChatGPT to extract sentiment polarity scores and we apply different models to forecast cumulative abnormal returns (CARs) in 30-minute intervals. Our findings reveal that sentiment – especially when captured immediately after news releases – has significant predictive power over intraday price movements. Strategies based on ChatGPT-derived sentiment consistently outperform benchmark models, particularly within the first two hours of trading. These results remain robust across alternative specifications and placebo tests, highlighting the value of LLMs for real-time market prediction. This research advances the literature on sentiment analysis and behavioral finance by linking emotion-driven news interpretation to high-frequency trading performance.
  • Thumbnail Image
    Publication
    Open Access
    Large scale analysis of open MOOC reviews to support learners’ course selection
    (Elsevier, 2022-12-30) Gomez, Manuel J.; Calderón, Mario; Sánchez, Víctor; García Clemente, Félix J.; Ruipérez Valiente, José A.; Ingeniería de la Información y las Comunicaciones
    The recent pandemic has changed the way we see education. During recent years, Massive Open Online Course (MOOC) providers, such as Coursera or edX, are reporting millions of new users signing up on their platforms. Though online review systems are standard among many verticals, no standardized or fully decentralized review systems exist in the MOOC ecosystem. In this vein, we believe that there is an opportunity to leverage available open MOOC reviews in order to build simpler and more transparent reviewing systems, allowing users to really identify the best courses out there. Specifically, in our research we analyze 2.4 million reviews (which is the largest MOOC reviews dataset used until now) from five different platforms in order to determine the following: (1) if the numeric ratings provide discriminant information to learners, (2) if NLP-driven sentiment analysis on textual reviews could provide valuable information to learners, (3) if we can leverage NLP-driven topic finding techniques to infer themes that could be important for learners, and (4) if we can use these models to effectively characterize MOOCs based on the open reviews. Results show that numeric ratings are clearly biased (63% of them are 5-star ratings), and the topic modeling reveals some interesting topics related with course advertisements, the real applicability, or the difficulty of the different courses.
  • Thumbnail Image
    Publication
    Open Access
    Las leyes sobre la violencia de género y doméstica en España y Reino Unido y la emoción: un estudio léxico del discurso jurídico desde el análisis del sentimiento.
    (Escola d´Administració Pública de Catalunya, 2019-06-12) Orts Llopis, María Ángeles; Traducción e Interpretación
    El objetivo último de este trabajo es realizar un estudio cuantitativo y cualitativo que evidencie que la forma en la que están verbalizadas las dos leyes que regulan la violencia de género y doméstica en España e Inglaterra desde el punto de vista léxico tiene mucho que ver con los objetivos políticos o sociológicos que la ley se propone abordar. El artículo analiza lo que Garofalo (2017: 56) denomina “ítems axiológicos” o unidades léxicas valorativas que expresan la involucración emocional en las leyes y cómo se dan de diferente manera dependiendo de la cultura jurídica de que se trate. El corpus analizado se compone de la Ley Orgánica española 1/2004 de Medidas de Protección Integral contra la Violencia de Género, y la Ley de 2004 sobre Violencia Doméstica, Delitos en el Hogar y sus Víctimas, de Inglaterra y Gales. El análisis consta de dos fases: la primera lleva a cabo un procesamiento automático por medio de Antconc 2.0 (Anthony, 2014), con el fin de obtener una lista de palabras clave indicadoras de la relevancia y frecuencia en cada corpus de los términos que pertenecen al ámbito del lenguaje jurídico y de aquellos que conceptualizan el marco conceptual de la violencia doméstica y de género, respectivamente. En la segunda fase se ha utilizado la perspectiva del análisis del sentimiento y, más específicamente, el programa Lingmotif v.1.0 (Moreno Ortiz, 2017), con el fin de estudiar la polaridad (positiva, negativa o neutra) y la intensidad de sentimiento de estos textos legislativos, a través de un análisis léxico pormenorizado llevado a cabo por dicho programa. -------------------------
  • Thumbnail Image
    Publication
    Open Access
    Methodology for measuring individual affective polarization using sentiment analysis in social networks
    (2024-07-22) Martínez España, Raquel; Fernández-Pedauye, Julio; Giner-Pérez de Lucia, José; Rojo Martínez, José Miguel; Bakdid-Albane, Kaoutar; García Escribano, Juan José; Sociología; Facultad de Trabajo Social
    Affective polarization has important consequences for societies and institutions. At the institutional level, it hinders agreement among political actors, which damages the stability of the system. At the social level, it increases tensions and conflicts between people, damaging coexistence. Until now, affective polarization has been studied essentially through surveys, which are generally very costly if large and representative samples are to be obtained and in which the answers of the interviewees may not be totally sincere. Through this article, we apply sentiment analysis techniques to measure affective polarization without resorting to surveys, simply by monitoring the non-self-reported behavior of individuals in social networks. To do that, a novel methodology and a new indicator of affective polarization has been proposed using data from social networks. The proposed methodology and new indicator have been applied to the real case study of the regional elections in Spain, specifically to the autonomous Region of Murcia. The application of the methodology has been satisfactory, as well as that of the new indicator of affective polarization, providing a cost-effective way of calculating polarization. The results show that all political groups are polarized to a greater or lesser extent. Furthermore, the results conclude that the winning ideology in the elections, i.e., the right, was the one whose supporters behaved differently from the supporters of other ideologies.
  • Thumbnail Image
    Publication
    Open Access
    Smart analysis of economics sentiment in Spanish based on linguistic features and transformers
    (IEEE, 2023-02-10) García Díaz, José Antonio; García-Sánchez, Francisco ; Valencia García, Rafael; Informática y Sistemas; Facultad de Informática
    Texts related to economics and finances are characterized by the use of words and expressions whose meaning (and the sentiments they convey) substantially depend on the context. This poses a major challenge to Natural Language Processing tasks in general, and Sentiment Analysis in particular. For lowresource languages such as Spanish, this situation becomes even more acute. Yet, the latest advancements in the field, including word embeddings and transformers, have allowed to boost the performance of Sentiment Analysis solutions. In this work we explore the impact of the combination of different feature sets in the accuracy of Sentiment Analysis in Spanish financial texts. For this, a corpus with 15,915 tweets has been compiled and manually annotated as either positive, negative, or neutral. Then, feature sets based on contextual and non-contextual embeddings along with linguistic features were evaluated both individually and combined. The best results, with a weighted F1-score of 73.15880%, were obtained with a combination of feature sets by means of knowledge integration
  • Thumbnail Image
    Publication
    Open Access
    Textual analysis and sentiment analysis in accounting
    (Universidad de Murcia, Servicio de Publicaciones, 2021) Gandía, Juan L.; Huguet, David
    In spite of the relatively scarce use of textual analysis and sentiment analysis techniques in finance and accounting, they have great potential in accounting, both because of the volume of documents used for the communication of information and due to the growth in the use of digital tools and social media. In that regard, these techniques of analysis may help researchers to analyse hidden clues or look for additional information to that one observed through financial information, increasing the quantity and quality of the information traditionally used, and providing a new perspective of analysis. The aim of this study is to review the use of textual analysis and sentiment analysis in accounting. After presenting the concepts of textual analysis and sentiment analysis and expose their interest in accounting, we perform a review of the previous literature on the use of these techniques in finance and accounting and describe the main techniques of sentiment analysis, as well as the procedure to be followed for the use of this methodology. Finally, we suggest three lines of future research that may benefit from the use of textual and sentiment analysis.
  • Thumbnail Image
    Publication
    Embargo
    The English Supreme Court vs Boris Johnson: legal metaphors for a constitutional crisis
    (Peter Lang, 2021) Orts Llopis, María Ángeles; Traducción e Interpretación
    Legal metaphors are intrinsic to judicial reasoning: courts need onto-logical metaphors to establish the law as a powerful reality in the public uncon-scious; they are hackneyed metaphorical projections peculiar to legal discourse automatically and unsubconsciously deployed to convey the authoritativeness of the law to its subjects􀀌 At the same time, ordinary texts such as news articles, op- eds and editorials deploy a series of poetic, emotional metaphors that are key to disseminate judicial decisions, and which have an enormous impact on societal perceptions, symbols and interpretations of legal rulings􀀌 Our study examines the British constitutional crisis in the summer of 2019 and the Supreme Court ruling that ensued􀀌 The text of that ruling, plus a 20- thousand- word ad hoc sub-corpus containing a series of columns and editorials discussing the aftermath of the ruling constitute the corpora used􀀌 A previous study on lexical frequencies is undertaken to provide a first approach to the patterns of conceptualization of the metaphors describing the constitutional crisis, and mainly focusing upon emotion- free technolects and metaphorical clichés􀀌 Secondly, an automatic pro-cessing with Lingmotif (Moreno Ortiz, 2017), is deployed to more accurately establish the emotional (positive and negative) polarities in the texts and spot the emotional intensity in the different metaphorical areas􀀌 A final categorization of the source and target domains as discourse (power) and poetic (sentiment) met-aphors in either subcorpus within the framework of Appraisal Theory is made􀀌 Overall, our results must show how discourse metaphors establishing the author-ity of the Supreme Court are predominant in the ruling, while emotion-l aden, poetic metaphors are common in newspaper articles, as sentimental responses to such decisions