Suchergebnisse
Filter
37 Ergebnisse
Sortierung:
SSRN
Working paper
Deception in Speeches of Candidates for Public Office
International audience ; The contribution of this article is twofold: the adaptation and application of models of deception from psychology, combined with data-mining techniques, to the text of speeches given by candidates in the 2008 U.S. presidential election; and the observation of both short-term andmedium-term differences in the levels of deception. Rather than considering the effect of deception on voters, deception is used as a lens through which to observe the self-perceptions of candidates and campaigns. The method of analysis is fully automated and requires no human coding, and so can be applied to many other domains in a straightforward way. The authors posit explanations for the observed variation in terms of a dynamic tension between the goals of campaigns at each moment in time, for example gaps between their view of the candidate's persona and the persona expected for the position; and the difficulties of crafting and sustaining a persona, for example, the cognitive cost and the need for apparent continuity with past actions and perceptions. The changes in the resulting balance provide a new channel by which to understand the drivers of political campaigning, a channel that is hard to manipulate because its markers are created subconsciously.
BASE
Empirical Assessment of Al Qaeda, ISIS, and Taliban Propaganda
SSRN
Working paper
Evaluating the Interdisciplinary Mission of Small Group Research Using Computational Analytics
In: Small group research: an international journal of theory, investigation, and application, Band 49, Heft 4, S. 391-408
ISSN: 1552-8278
Richard Kettner-Polley and Charles Gavin founded Small Group Research ( SGR) to present research, build theory, and generally advance the study of small groups by combining insights from multiple disciplines. Currently, we evaluate the extent to which this interdisciplinary mission has been upheld over time. To do this, we apply the perspective and tools of big data analytics to the nearly 3 million words that span the 829 articles that comprise the SGR corpus from February 1990 to June 2017. Keyword analysis, ontological ordering, and interdisciplinary content analyses identify intriguing patterns and detect latent trends. Our results speak to the consistent interdisciplinarity of SGR while identifying opportunities for further development and more complex disciplinary integration in research on small groups.
Privacy engineering for learning analytics in a global market: Defining a point of reference
Purpose: Privacy is a culturally universal process; however, in the era of Big Data privacy is handled very differently in different parts of the world. This is a challenge when designing tools and approaches for the use of Educational Big Data (EBD) and learning analytics (LA) in a global market. The purpose of this paper is to explore the concept of information privacy in a cross-cultural setting to define a common point of reference for privacy engineering. Design/methodology/approach: The paper follows a conceptual exploration approach. Conceptual work on privacy in EBD and LA in China and the west is contrasted with the general discussion of privacy in a large corpus of literature and recent research. As much of the discourse on privacy has an American or European bias, intimate knowledge of Chinese education is used to test the concept of privacy and to drive the exploration of how information privacy is perceived in different cultural and educational settings. Findings: The findings indicate that there are problems using privacy concepts found in European and North-American theories to inform privacy engineering for a cross-cultural market in the era of Big Data. Theories based on individualism and ideas of control of private information do not capture current global digital practice. The paper discusses how a contextual and culture-aware understanding of privacy could be developed to inform privacy engineering without letting go of universally shared values. The paper concludes with questions that need further research to fully understand information privacy in education. Originality/value: As far as the authors know, this paper is the first attempt to discuss – from a comparative and cross-cultural perspective – information privacy in an educational context in the era of Big Data. The paper presents initial explorations of a problem that needs urgent attention if good intentions of privacy supportive educational technologies are to be turned into more than political slogans. ; acceptedVersion
BASE
From Ethics to Analytics: Aspects of Participants' Orientations to the Presence and Relevance of Recording Devices
In: Sociology: the journal of the British Sociological Association, Band 37, Heft 2, S. 315-337
ISSN: 1469-8684
In discussions of sociological research based on the recording of interactional occasions, participants' awareness of the presence of recording devices is often deemed to have a detrimental effect on the `authenticity' or `naturalness' of the data collected. We propose an alternative approach to this issue by seeking to turn participants' observable orientations to the presence and relevance of recording devices into an analytic topic, and exploring the precise kinds of situated interactional work in which such orientations are involved. Drawing on a substantial data corpus from three distinct research settings, we analyse a range of interactional functions associated with participants' orientations to the fact of their talk being recorded. Instead of assuming that it will act as a constraint on the production of `natural' talk, we show how the relevance of a recording device is negotiated and used in situ as a participants' matter and interactional resource.
Supporting Methodology Transfer inVisualization Research with Literature-Based Discovery and Visual Text Analytics. Ph.D. thesis (presentation slides)
Presentation slides for Alejandro Benito-Santos' Ph.D. thesis: "Supporting Methodology Transfer in Visualization Research with Literature-Based Discovery and Visual Text Analytics." Abstract: The increasing specialization of science has recently motivated a rapid fragmentation of well-established disciplines into communities of interdisciplinary practice. This decomposition can be observed in a type of visualization practice known as problem-driven visualization research. Here, interdisciplinary teams of domain and visualization experts collaborate in a specific area of knowledge such as the digital humanities, bioinformatics, computer security, or sports science. This thesis proposes a series of methods inspired by recent advances in automated text analysis and knowledge representation to promote adequate communication and transference of knowledge between these communities. The discovered methods were combined into a visual text analytics interface for scientific discovery, GlassViz, that was designed with these aims in mind. The tool was first tested in the digital humanities domain to explore a large corpus of general-purpose visualization papers. GlassViz was adapted in a later study to support different data sources representative of these communities, showing evidence that the proposed approach is also a valid alternative to address the fragmentation problem in visualization research.
BASE
Curating Social Media Data
Social media platforms have empowered the democratization of the pulse of people in the modern era. Due to its immense popularity and high usage, data published on social media sites (e.g., Twitter, Facebook and Tumblr) is a rich ocean of information. Therefore data-driven analytics of social imprints has become a vital asset for organisations and governments to further improve their products and services. However, due to the dynamic and noisy nature of social media data, performing accurate analysis on raw data is a challenging task. A key requirement is to curate the raw data before fed into analytics pipelines. This curation process transforms the raw data into contextualized data and knowledge. We propose a data curation pipeline, namely CrowdCorrect, to enable analysts cleansing and curating social data and preparing it for reliable analytics. Our pipeline provides an automatic feature extraction from a corpus of social media data using existing in-house tools. Further, we offer a dual-correction mechanism using both automated and crowd- sourced approaches. The implementation of this pipeline also includes a set of tools for automatically creating micro- tasks to facilitate the contribution of crowd users in curating the raw data. For the purposes of this research, we use Twitter as our motivational social media data platform due to its popularity.
BASE
The problem of the status of the Holy Places in Jerusalem and its impact on the Palestinian-Israeli conflict
In: Journal of International Analytics, Heft 2, S. 67-82
ISSN: 2541-9633
This article focuses on the legal status of Jerusalem - one of the most complex and debated issues of international law and international politics. Before the establishment of Israel in 1948, over the centuries in the Ottoman period and the years of the British Mandate there was no legally binding bilateral or international treaty that would clearly define the legal status of Jerusalem. However, both the Turkish authorities and the British administration in Palestine preceding from the fact that Jerusalem is the center of three world religions, fully ensured of the rights of believers of all confessions. In accordance with the well-known international instruments of law all Jerusalem should be a special territory of Corpus Separatum, which will be subjected to the international control (UN General Assembly Resolution 181 / II of 29 November 1947). However, in 1980 the Israeli Parliament declared Jerusalem the «eternal and undivided capital» of Israel, including the Arab territories of East Jerusalem occupied in 1967. This law, as well as the Israeli law on the protection of the Holy Places has radically changed the Status quo which existed for centuries. No country in the world recognizes Israel's attempts to change the legal Status of the City. In the present article the following aspects are analyzed: • The Status of the Holy Places in Jerusalem, before the establishment of the British mandate over Palestine in 1922; • The Status of the Holy Places in Jerusalem in accordance with the international law instruments; • The Status of the Holy Places in Jerusalem after the partition of the City on the Israeli and Jordanian enclaves in 1948; • Change of the Status of the Holy Places of Jerusalem after the June 1967 War and the impact of this transformation both on the Arab-Israeli and the Palestinian-Israeli conflicts; • Actions taken by Israel to change the Status of the Temple Mount; • The problem of the Status of Jerusalem in the Palestinian-Israeli Peace Process.
Is it about "them"? leveraging big data research to understand anti-immigrant discourse
In: Big data & society, Band 11, Heft 2
ISSN: 2053-9517
The paper explores the potential of big data analytics for researching anti-immigrant discourse. We emphasize contextualization as an essential element of research and follow a hybrid approach inspired by best practices of computational content analysis, combining human hermeneutic expertise with supervised machine learning to classify a corpus of comments in online news communities in Singapore over 6 months ( N = 399,225). The paper highlights how big data analytics can provide a nuanced and critical apprehension of immigrant-related discourse in large social media datasets.
"His tweets speak for themselves": An analysis of Donald Trump's Twitter behaviour
This is a conference paper. ; We explore President Donald Trump's tweeting habits and the effects they have on his followers and the American media. To gain a comprehensive picture of Trump's tweeting habits as President of the United States, we have undertaken a study of Trump's personal @realDonaldTrump Twitter account, focusing on his campaign, the transition period before his presidency, and first 200 days in office. We employ three state-ofthe-art computational tools to analyse sentiment, emotions and psycholinguistic features in Trump's tweets to decipher what it is about his communication methods that generates the highest responses and retweets. We find that during the first 200 days of presidency, an accusative tone of discourse was most frequently used by @realDonaldTrump, and among a number of significant emotional patterns, we observe an intriguing correlation in that the more negative the overall message of a tweet is, the more likely it is to be re-tweeted, favourited, and discussed in American mainstream media. We also used data from the recently released PTDC corpus (Political Twitter Discourse Corpus) consisting of 205,303 original tweets of all current US state governors, members of the US Senate, and members of Congress and found that Trump's tweeting style is significantly different along a central dimension of language on Twitter. Our findings suggest that the general public on Twitter respond more actively to negative and less analytic language, and in turn, the language on Twitter directed at Trump is highly emotional and often contains negative sentiment.
BASE
Analyzing a Decade of Wind Turbine Accident News with Topic Modeling
Despite the significance and growth of wind energy as a major source of renewable energy, research on the risks of wind turbines in the form of accidents and failures has attracted limited attention. Research that applies data analytics methodologically in this context is scarce. The research presented here, upon construction of a text corpus of 721 selected wind turbine accident and failure news reports, develops and applies a custom-developed data analytics framework that integrates tabular analysis, visualization, text mining, and machine learning. Topic modeling was applied for the first time to identify and classify recurring themes in wind turbine accident news, and association mining was applied to identify contextual terms associated with death and injury. The tabular and visual analyses relate accidents to location (offshore vs. onshore), wind turbine life cycle phases (transportation, construction, operation, and maintenance), and the incidence of death and injury. As one of the insights, more incidents were found to occur during operation and transportation. Through topic modeling, topics associated most with deaths and injuries were revealed. The results could benefit wind turbine manufacturers, service providers, energy companies, insurance companies, government bodies, non-profit organizations, researchers, and other stakeholders in the wind energy sector.
BASE
myDIG: Personalized Illicit Domain-Specific Knowledge Discovery with No Programming
In: Future Internet ; Volume 11 ; Issue 3
With advances in machine learning, knowledge discovery systems have become very complicated to set up, requiring extensive tuning and programming effort. Democratizing such technology so that non-technical domain experts can avail themselves of these advances in an interactive and personalized way is an important problem. We describe myDIG, a highly modular, open source pipeline-construction system that is specifically geared towards investigative users (e.g., law enforcement) with no programming abilities. The myDIG system allows users both to build a knowledge graph of entities, relationships, and attributes for illicit domains from a raw HTML corpus and also to set up a personalized search interface for analyzing the structured knowledge. We use qualitative and quantitative data from five case studies involving investigative experts from illicit domains such as securities fraud and illegal firearms sales to illustrate the potential of myDIG.
BASE
Scientific Information Analysis Using Text Analysis Tool "Voyant Tools"
In: Information & Media: scholarly journal : mokslo žurnalas/ Vilnius University, Band 97, S. 25-48
ISSN: 2783-6207
This article describes the use of "Voyant Tools", an open access text analysis application, to examine a corpus of articles from open access journals, dealing with the topic of digital humanities. The corpus consisted of 404 articles recorded in the "Clarivate Analytics Web of Science" and "Scopus ScienceDirect" databases. The authors discuss how "Voyant Tools" aids to identify the dominant fields of research through quantitative methods and to reveal the main discourse themes using distant reading and interactive reading capabilities. They also identify some problems encountered during the analyses, and also discuss the usefulness of data visualization for research and interpretation. Computer tools can be useful for experienced researchers who are interested in quantitative text analysis, as well as for beginners, as it provides an opportunity to acquire basic knowledge that will lead to a deeper interest in textual analysis methods.
CUTE - CRETA Un-/Shared Task zu Entitätenreferenzen
Dies ist die Veröffentlichung eines shared/unshared Task Workshops (entwickelt in CRETA: Center for Reflected Text Analytics), der im Rahmen der DHd 2017 in Bern (CH) stattfand. Im Gegensatz zu shared tasks, bei denen die Performanz verschiedener Systeme/Ansätze/Methoden direkt anhand einer klar definierten und quantitativ evaluierten Aufgabe verglichen wird, sind unshared tasks offen für verschiedenartige Beiträge, die auf einer gemeinsamen Datensammlung basieren. Shared und Unshared Tasks in den Digital Humanities sind ein vielversprechender Weg, Kollaboration und Interaktion zwischen Geistes-, Sozial- und ComputerwissenschaftlerInnen zu fördern und zu pflegen. Konkret riefen wir dazu auf, gemeinsam an einem heterogenen Korpus zu arbeiten, in dem Entitätenreferenzen annotiert wurden. Das Korpus besteht aus Parlamentsdebatten des Deutschen Bundestags, Briefen aus Goethes Die Leiden des jungen Werther, einem Abschnitt aus Adornos Ästhetischer Theorie und den Büchern von Wolframs von Eschenbach Parzival (mittelhochdeutsch). Auch wenn jede Textsorte ihre eigenen Besonderheiten hat, wurden alle nach einheitlichen Annotationsrichtlinien annotiert, die wir auch zur Diskussion stellten. Wir veröffentlichen hier den Aufruf zu Workshop-Beiträgen, die Annotationsrichtlinien, die Korpusdaten samt Beschreibung und die einführenden Vortragsfolien des Workshops. ; This is the publication of an shared/unshared task workshop (developed in CRETA: Center for Reflected Text Analytics), which was held during DHd 2017, Bern, Switzerland. While shared tasks are used as a direct benchmark for different systems/approaches/methods on a clearly defined and evaluated task, unshared tasks are open to various kinds of contributions, based on a common data set. Shared and unshared tasks in the fields of digital humanities are a promising way of fostering collaboration and interaction between Humanities scholars and Computer Science researchers. Specifically, we invited scholars, researchers and scientists to collaboratively work on a heterogeneous, German-language corpus that has been annotated with entity references. The corpus comprises the following texts: debates from the German national parliament (Bundestag), letters from Goethe's The Sorrows of Young Werther, a segment from Adornos Ästhetische Theorie, and books of Wolfram's von Eschenbach Parzival. Each text (and genre) has its own characteristics. Nevertheless, all annotators followed the same uniform annotation guidelines which were also discussed. Here we publish the call for submissions to the workshop, the annotation guidelines (in German), the corpus data together with their description, and the introductory slides to the workshop.
BASE