Search

This open access book offers a comprehensive overview of available techniques and approaches to explore large social media corpora, using as an illustrative case study the Coronavirus Twitter corpus. First, the author describes in detail a number of methods, strategies, and tools that can be used to access, manage, and explore large Twitter/X corpora, including both user-friendly applications and more advanced methods that involve the use of data management skills and custom programming scripts. He goes on to show how these tools and methods are applied to explore one of the largest Twitter datasets on the COVID-19 pandemic publicly released, covering the two years when the pandemic had the strongest impact on society. Specifically, keyword extraction, topic modelling, sentiment analysis, and hashtag analysis methods are described, contrasted, and applied to extract information from the Coronavirus Twitter Corpus. The book will be of interest to students and researchers in fields that make use of big data to address societal and linguistic concerns, including corpus linguistics, sociology, psychology, and economics.

This book provides a broad overview of the state of the art of the research in generative methods for the analysis of social media data. It especially includes two important aspects that currently gain importance in mining and modelling social media: dynamics and networks. The book is divided into five chapters and provides an extensive bibliography consisting of more than 250 papers. After a quick introduction and survey of the book in the first chapter, chapter 2 is devoted to the discussion of data models and ontologies for social network analysis. Next, chapter 3 deals with text generation and generative text models and the dangers they pose to social media and society at large. Chapter 4 then focuses on topic modelling and sentiment analysis in the context of social networks. Finally, Chapter 5 presents graph theory tools and approaches to mine and model social networks. Throughout the book, open problems, highlighting potential future directions, are clearly identified. The book aims at researchers and graduate students in social media analysis, information retrieval, and machine learning applications.

This book includes chapters which discuss effective and efficient approaches in dealing with various aspects of social media analysis by using machine learning techniques from clustering to deep learning. A variety of theoretical aspects, application domains and case studies are covered to highlight how it is affordable to maximize the benefit of various applications from postings on social media platforms. Social media platforms have significantly influenced and reshaped various social aspects. They have set new means of communication and interaction between people, turning the whole world into a small village where people with internet connect can easily communicate without feeling any barriers. This has attracted the attention of researchers who have developed techniques and tools capable of studying various aspects of posts on social media platforms with main concentration on Twitter. This book addresses challenging applications in this dynamic domain where it is not possible to continue applying conventional techniques in studying social media postings. The content of this book helps the reader in developing own perspective about how to benefit from machine learning techniques in dealing with social media postings and how social media postings may directly influence various applications.

This book provides a comprehensive overview of the theory and praxis of Big Data Analytics and how these are used to extract cognition-related information from social media and literary texts. It presents analytics that transcends the borders of discipline-specific academic research and focuses on knowledge extraction, prediction, and decision-making in the context of individual, social, and national development. The content is divided into three main sections: the first of which discusses various approaches associated with Big Data Analytics, while the second addresses the security and privacy of big data in social media, and the last focuses on the literary text as the literary data in Big Data Analytics. Sharing valuable insights into the etiology behind human cognition and its reflection in social media and literary texts, the book benefits all those interested in analytics that can be applied to literature, history, philosophy, linguistics, literary theory, media & communication studies and computational/digital humanities.

Hunderte von Millionen Blogs auf Plattformen wie Tumblr, Pinterest, Flickr, Instagram usw. Milliarden Bilder, in jeder Sekunde gepostet, geliked, geteilt, modifiziert und neu arrangiert – eine Wetterküche für das Geschmacksklima von morgen! Wie funktioniert diese Kommunikation? Wie lassen sich Bilder analysieren und die in ihnen enthaltenen Informationen in Bezug auf zukünftige Entwicklungen interpretieren? Insgesamt fünf Research Units aus 60 Digital Natives mit umfangreichen Erfahrungen in Statistik, Empirie und Konsumtheorien haben unter Leitung des Autors ein Jahr lang in Befragungen, Gesprächen, quantitativen Analysen von Blogs, in Experimental-Settings und in einer Analyse der Vorstellungen von Big Data-Protagonisten die Szene durchforscht. Die Befunde offenbaren die latenten Muster und Attraktoren dieser Kommunikation, ihre durch Random Copying-Prozesse bewegte Dynamik und Volatilität. Vor allem, was die einschlägige Diskussion um die Rolle und die Möglichkeiten von Big Data-Analysen im Bereich soziokultureller Phänomene angeht, wird die wachsende Bedeutung der Soziologie sichtbar. Ein Cultural Turn der Digitalisierung und der Predictive Analytics zeichnet sich ab.