Suchergebnisse

Part I Statistical methods for Textual Data Analysis -- Statistical and deep learning methods for a linguistic and literary analysis -- Statistical profiling of Hybrid CNN-SVM effectiveness -- EMOtivo: a classifier for emotion detection of Italian texts trained on a self-labelled corpus -- Community detection and semantic analysis on Twitter. The case of No greenpass and No vax movement in Italy -- Evaluating customer satisfaction through Amazon reviews analysis: the Bluetooth earphones example -- Symmetric Non-Negative Matrix Factorization for analysing the scientific production on day surgery -- Social Media Effects on Sales: consumer sentiment in a state-space model -- Part II Advances in language processing -- Quality enhancements in experimental statistics: the Italian Social Mood on Economy Index -- A Strategy to Identify the Peculiarity of a Lexicon in the Analysis of a Corpus -- Neologisms and estrangement in a corpus of science-fiction -- Automatic retrieving ofderived Quechua verbs -- A Stylometric profile of Carmen Mola in the gender of 'her' authorial persona and the contribution of each author behind the pseudonym -- Automatic Genre Classification of Czech Texts Based on Syntactic Functions -- Deep learning as an aid to text mining in the choice of texts to lemmatise for a comparison corpus: a stylistic study of Peter Damian's letters -- Dialogic Process Analysis in Natural Language Processing: an attempt to describe sense of reality and meaning of textdata -- Multi-channel Convolutional Transformer and intertextuality: a Latin case study -- Part III Emotional and Sentiment Analyses -- Opinion Mining Hybrid Approach. An application to investigate the users' political positions in disinformative echo chambers -- Prediction of Italians' sentiment during the first COVID-19 lockdown through a weighted random forest balanced with SMOTE algorithm -- Sentiment analysis on social network data: the Regional Index RETI -- Integrating text mining and hermeneutic analysis: the case of international volunteering biographies -- Emotional text mining and multilingual corpora: The analysis of #Covid-19 on Twitter -- Emotional Markers as Indicators of Investor Attitudes: EDA Sub - Process Proposal -- "The Spanish Model": an analysis of Spanish culture in Organ Donation through the Emotional Text Mining -- Part IV Textual Data Analysis in action -- Comparative analysis of national reports: the case of the Erasmus+ ECOLHE Project -- Action Research in Psychology: the case of adoptive family -- Uncovering Uncertainty in Narrative Economics: A Semantic Search Approach -- Italian Institutional communication in pandemic period: a chronological analysis of Prime Minister speeches -- What about corruption? A text analytics method for a scoping literature review -- The stability of the discursive framework of the Ministry of Foreign Affairs tested by textometry -- Statistical analysis of textual data for longitudinal analysis. A studyon postgraduate course participants' reflections -- Third Mission & VQR 2015-2019: A Bigram's Story.

In this paper, we address exploratory analysis of textual data streams and we propose a bootstrapping process based on a combination of keyword similarity and clustering techniques to: (i) classify documents into fine-grained similarity clusters, based on keyword commonalities; (ii) aggregate similar clusters into larger document collections sharing a richer, more user-prominent keyword set that we call topic; (iii) assimilate newly extracted topics of current bootstrapping cycle with existing topics resulting from previous bootstrapping cycles, by linking similar topics of different time periods, if any, to highlight topic trends and evolution. An analysis framework is also defined enabling the topic-based exploration of the underlying textual data stream according to a thematic perspective and a temporal perspective. The bootstrapping process is evaluated on a real data stream of about 330.000 newspaper articles about politics published by the New York Times from Jan 1st 1900 to Dec 31st 2015.

AbstractThe inherent qualitative nature of textual data poses significant challenges for direct integration into statistical models. This paper presents a two-stage process for analyzing longitudinal textual data, offering a solution to this inherent challenge. The proposed model comprises (1) initial data preprocessing and sentiment extraction, followed by (2) applying a growth curve model to analyze the extracted sentiments directly. The paper also explores four distinct approaches for extracting sentiment scores in the dialogue, providing versatility to the proposed framework. The practical application of the proposed model is demonstrated through the analysis of an empirical longitudinal textual dataset. This framework offers a valuable contribution to the field by addressing the challenges associated with modeling qualitative textual data, providing a robust methodology for extracting and analyzing sentiments longitudinally.

Analyse- und Visualisierungsverfahren des Textual Data-Minings finden zunehmend auch in der qualitativen Sozialforschung Anwendung. Damit gehen konzeptionelle Überlegungen einher, solche Verfahren direkt in Forschungsprozesse einzubetten. Im Gegensatz zu einer wechselseitigen Kombination von digitalen und qualitativen Methoden argumentieren wir für eine nachgeordnete Nutzung des Textual Data-Minings, die sich auf sprachstatistische Analyseschritte zum Zweck eines Computational Sensitizing beschränkt. Mit computationaler Sensibilisierung meinen wir eine Perspektivenerweiterung: Textual Data-Mining dient dann - wie bisher Vorwissen und Theorien - allein dazu, Fragen an und veränderte Sichtweisen auf das Material anzuregen. Im Beitrag veranschaulichen wir exemplarisch an einem Projekt aus der Bildungsforschung, wie Ergebnisse des Textual Data-Minings für Besonderheiten in den qualitativen Daten sensibilisieren können.

In this work we present a semantic framework suitable of being used as support tool for recommender systems. Our purpose is to use the semantic information provided by a set of integrated resources to enrich texts by conducting different NLP tasks: WSD, domain classification, semantic similarities and sentiment analysis. After obtaining the textual semantic enrichment we would be able to recommend similar content or even to rate texts according to different dimensions. First of all, we describe the main characteristics of the semantic integrated resources with an exhaustive evaluation. Next, we demonstrate the usefulness of our resource in different NLP tasks and campaigns. Moreover, we present a combination of different NLP approaches that provide enough knowledge for being used as support tool for recommender systems. Finally, we illustrate a case of study with information related to movies and TV series to demonstrate that our framework works properly. ; This research work has been partially funded by the University of Alicante, Generalitat Valenciana, Spanish Government and the European Commission through the Projects, TIN2015-65136-C2-2- R, TIN2015-65100-R, SAM (FP7-611312), and PROMETEOII/2014/001.

As qualitative research has evolved, researchers now often combine interviews with the production of photographs, artefacts, collages, maps or drawings and the like. However, in practice, the artefacts produced are used to eliciting experiences and stimulating conversations rather than as data, per se, which is often due to the lack of guidelines for how to deal with the artefacts as data in a systematic analytical process. In this article, we present the Systematic Visuo-Textual Analysis, a framework developed to provide much-needed support for qualitative researchers in analysing artefacts in combination with interviews. Drawing on existing frameworks for visual and textual analysis the focus of this framework is to analyse visual and textual datasets separately and in conjunction with one another through several levels of interpretation from noticing descriptive elements and focussing on specific linguistic and artistic elements through to developing conceptual themes. Drawing on examples from our own research, we will demonstrate the practical application of the Systematic Visuo-Textual Analysis.

Nowadays, information and communications technology systems are fundamental assets of our social and economical model, and thus they should be properly protected against the malicious activity of cybercriminals. Defence mechanisms are generally articulated around tools that trace and store information in several ways, the simplest one being the generation of plain text files coined as security logs. Such log files are usually inspected, in a semi-automatic way, by security analysts to detect events that may affect system integrity, confidentiality and availability. On this basis, we propose a parameter-free method to detect security incidents from structured text regardless its nature. We use the Normalized Compression Distance to obtain a set of features that can be used by a Support Vector Machine to classify events from a heterogeneous cybersecurity environment. In particular, we explore and validate the application of our method in four different cybersecurity domains: HTTP anomaly identification, spam detection, Domain Generation Algorithms tracking and sentiment analysis. The results obtained show the validity and flexibility of our approach in different security scenarios with a low configuration burden ; This research has received funding from the European Union's Horizon 2020 Research and Innovation Programme under grant agreement No. 872855 (TRESCA project), from the Comunidad de Madrid (Spain) under the projects CYNAMON (P2018/TCS-4566) and S2017/BMD-3688, co-financed with FSE and FEDER EU funds, by the Consejo Superior de Investigaciones Científicas (CSIC) under the project LINKA20216 ("Advancing in cybersecurity technologies", i-LINK+ program), and by Spanish project MINECO/FEDER TIN2017-84452-R

14 páginas; 11 tablas; 1 figura ; Nowadays, information and communications technology systems are fundamental assets of our social and economical model, and thus they should be properly protected against the malicious activity of cybercriminals. Defence mechanisms are generally articulated around tools that trace and store information in several ways, the simplest one being the generation of plain text files coined as security logs. Such log files are usually inspected, in a semi-automatic way, by security analysts to detect events that may affect system integrity, confidentiality and availability. On this basis, we propose a parameter-free method to detect security incidents from structured text regardless its nature. We use the Normalized Compression Distance to obtain a set of features that can be used by a Support Vector Machine to classify events from a heterogeneous cybersecurity environment. In particular, we explore and validate the application of our method in four different cybersecurity domains: HTTP anomaly identification, spam detection, Domain Generation Algorithms tracking and sentiment analysis. The results obtained show the validity and flexibility of our approach in different security scenarios with a low configuration burden. ; This research has received funding from the European Union's Horizon 2020 Research and Innovation Programme under grant agreement No. 872855 (TRESCA project), from the Comunidad de Madrid (Spain) under the projects CYNAMON (P2018/TCS-4566) and S2017/BMD-3688, co-financed with FSE and FEDER EU funds, by the Consejo Superior de Investigaciones Científicas (CSIC) under the project LINKA20216 ("Advancing in cybersecurity technologies", i-LINK+ program), and by Spanish project MINECO/FEDER TIN2017-84452-R.

AbstractUnderlying information about failure, including observations made in free text, can be a good source for understanding, analyzing, and extracting meaningful information for determining causation. The unstructured nature of natural language expression demands advanced methodology to identify its underlying features. There is no available solution to utilize unstructured data for risk assessment purposes. Due to the scarcity of relevant data, textual data can be a vital learning source for developing a risk assessment methodology. This work addresses the knowledge gap in extracting relevant features from textual data to develop cause–effect scenarios with minimal manual interpretation. This study applies natural language processing and text‐mining techniques to extract features from past accident reports. The extracted features are transformed into parametric form with the help of fuzzy set theory and utilized in Bayesian networks as prior probabilities for risk assessment. An application of the proposed methodology is shown in microbiologically influenced corrosion‐related incident reports available from the Pipeline and Hazardous Material Safety Administration database. In addition, the trained named entity recognition (NER) model is verified on eight incidents, showing a promising preliminary result for identifying all relevant features from textual data and demonstrating the robustness and applicability of the NER method. The proposed methodology can be used in domain‐specific risk assessment to analyze, predict, and prevent future mishaps, ameliorating overall process safety.

This article presents the problems involved in implementing a semantic grammar on a computer. Semantic grammars provide powerful content analysis schemes for collecting data from textual sources (e.g., newspapers). Semantic grammars organize information hierarchically and relationally. The hierarchical organization of the data provides a simple way of aggregating information, and the relational organization of information provides explicit links between the basic elements of the grammar. These characteristics and the linguistic underpinnings of semantic grammars suggest a variety of features that a software of data collection based on a semantic grammar should have. These features are illustrated with respect to data entry, data aggregation, and data verification. It is argued that the complexity of semantic grammars as content analysis schemes, coupled with the on-line capacity of computers to perform data quality checks, produces richer and more reliable data than do traditional content analysis methodologies. It is shown that despite such data complexity, the relational organization of coded output provided by a semantic grammar allows researchers to retrieve data in highly flexible ways using powerful relational data base management systems.