Skip to main content
main-content

Über dieses Buch

This book reports on the latest advances in understanding human cognition and its interplay with various cultural constructs, such as geographical, historical, sociological, and organizational cultures. It addresses researchers, scholars, and industry practitioners from diverse backgrounds, including sociology, linguistics, business, military science, psychology, human factors, neuroscience, and education. The book covers a wealth of topics, such as the analyses of historical events and intercultural competence, commercial applications of social-cultural science, the study of decision-making similarities (and differences) across cultures, Human, Social, Cultural Behavioral (HSCB) modeling and simulation technology, as well as social networks and studies on group communication. It also reports on real-world case studies relevant to cross-cultural decision making. The book aims at combining neurocognitive studies with studies from other relevant disciplines to develop a more holistic understanding of the decisions that people, groups, and societies make to improve the ability to forecast and plan for the future. The book is based on the AHFE 2016 International Conference on Cross-Cultural Decision Making (CCDM), held on July 27-31, 2016, in Walt Disney World®, Florida, USA.

Inhaltsverzeichnis

Frontmatter

Dynamic PMESII Modeling in Complex Environments

Frontmatter

Expeditionary Modeling for Population-Centric Operations in Megacities: Some Initial Experiments

Fueled by globalization and urbanization, megacities are extreme exemplars of complex, population-centric operating environments by virtue of their size, density, complexity, and dynamism. These likely epicenters of future instability make them probable locations of future military operations. As the epitome of complex, population-centric operating environments, megacities and other dense urban areas are of increasing interest to the US military, particularly the Army. Today, course of action analysis for operations in these environments is limited by the availability of analyst expertise, relevant data, and time. This paper presents a future vision of Expeditionary Modeling in which ensembles of diverse computational models are rapidly assembled, tailored, and brought to bear to quantitatively characterize the likely direct and indirect effects of Diplomatic, Information, Military, and Economic (DIME) actions in these environments. This paper describes some preliminary experiments to demonstrate the feasibility of this model-based approach, leveraging extant models for human and urban terrain.
Brian Kettler, Jennifer Lautenschlager

Time-Series Analysis of Blog and Metaphor Dynamics for Event Detection

Open source indicators (OSI) like social media are useful for detecting and forecasting the onset and progression of political events and mass movements such as elections and civil unrest. Recent work has led us to analyze metaphor usage in Latin American blogs to model such events. In addition to being rich in metaphorical usage, these data sources are heterogeneous with respect to their time-series behavior in terms of publication frequency and metaphor occurrence that make relative comparisons across sources difficult. We hypothesize that understanding these non-normal behaviors is a compulsory step toward improving analysis and forecasting ability. In this work, we discuss our blog data set in detail, and dissect the data along several key characteristics such as blog publication frequency, length, and metaphor usage. In particular, we focus on occurrence clustering: modeling variations in the incidence of both metaphors and blogs over time. We describe these variations in terms of the shape parameters of distributions estimated using maximum likelihood methods. We conclude that although there may be no “characteristic” behavior in the heterogeneity of the sources, we can form groups of blogs with similar behaviors to improve detection ability.
Brian J. Goode, Juan Ignacio M. Reyes, Daniela R. Pardo-Yepez, Gabriel L. Canale, Richard M. Tong, David Mares, Michael Roan, Naren Ramakrishnan

Using Stories to Deepen Shared Human-Computer Understanding of PMESII Systems

Humans tend to represent and to understand the world in terms of stories, while computer reasoning tends to require formal, mathematical representations. This paper describes a research prototype that enables computers to parse human stories and use collections of those stories to inform causal modeling of political, military, economic, social, infrastructure, and information (PMESII) systems. We introduce the need for causal modeling, the approach we have taken in implementing an initial proof-of-concept and the results from pilot testing of the software that illustrates functional capabilities and opportunities for deepening story-based computer interpretation of stories.
Robert E. Wray, Jeremiah T. Folsom-Kovarik, Dylan Schmorrow, Randolph M. Jones, Robert Marinier

Modeling Causal Relationships in Sociocultural Systems Using Ensemble Methods

Analyzing the political, military, economic, social, information, and infrastructure (PMESII) effects in a sociocultural system requires models that capture the causal and predictive dynamics. However, given the complexity of PMESII factors and the diversity of available data sources, accurately modeling causal relationships requires incorporating multiple domains of study and a variety of analytic methods. In this paper, we present an ensemble approach to modeling causal relationships of sociocultural systems, applying insights from machine learning where ensembles consistently outperform individual approaches. We describe three different types of ensemble models and combinations and explore the application of this approach in experiments using both synthetic and real-world datasets.
Amy Sliva, Scott Neal Reilly, David Blumstein, Steve Hookway, John Chamberlain

Cross-Cultural Comparisons in Business, Education, and Outlook

Frontmatter

Difference Analysis of Impression on Japan from Chinese Students with Different Education Stages

In the same country the knowledge acquisition and understanding under the different cultural education stages have the slight differences which can reflect on the making decision especially for the first impression. In order to analysis the differences of the Chinese students’ first impressions towards Japan and the corresponding knowledge acquisition ways under Chinese different cultural education stages, we firstly used the questionnaire through the nine-in-one drawing method to obtain the accurate first impressions and corresponding knowledge acquisition ways data, the different stages consist of the junior school, senior high school, university stage major in Japanese and not major in Japanese. Secondly, paired-t-test method was employed to access the differences degree of impressions and ways between the different stages. The results by analyzing the above difference suggested that, the knowledge shortage and corresponding acquisition ways during the different cultural education stages can be summarized for educational leader to make the personalized and reasonable decision.
Xiaohong Zhang, Jianwen Xiang, Shengwu Xiong, Haowen Li, Bixiang Li

Dynamics of National Culture and Employee Characteristics on Organizational Commitment in Retail Banks in Ghana

Firms operating in high growth sectors are known to face the challenges of hiring and assimilating large numbers of new employees, providing new knowledge and skills to existing employees, and addressing the need for a rapid expansion of leadership capability. In the Ghanaian situation, such a challenge is known to prevail, since the country implemented major financial sector reforms starting in the late 1980s as part of its broad market reforms, key of which is the deregulation of the financial sub-sector. The banking sector in Ghana is therefore, faced with human resource management challenges, which includes the finding of the right caliber of employees to employ, and how to ensure that employees get committed to their organizations in order to reduce their desire to switch to competitor firms, due to apparent dissatisfaction with their jobs. This study therefore, examined a conceptual model that sought to hypothesize the impact of national culture and employee characteristics on employees’ organizational commitment in retail banks in Ghana. The purpose is to understand the extent to which Ghanaian national cultural values and employee characteristics impact on employee organizational commitment in Retail Banks operating in Ghana. Quantitative data was collected from 282 bank employee across nine different retail banks in Ghana, and analyzed stepwise, using the analysis of moment structures (AMOS) program. Firstly, path analysis was conducted to test the individual measurement models that constitute the various components of the conceptual structural model. In this analysis, the factor score weights and model fit estimates for the indicator variables in the various latent variables (i.e. national culture, employee characteristics, and organizational commitment,) were appraised. Results from the path analysis identified four measurable indicators for organizational commitment. The analysis showed that all the measurable indicators tested for national culture and employee characteristics did not have significant loads to serve as measurable indicators. It is concluded that employees’ organizational commitment in retail banks in Ghana is neither influenced by the Ghanaian national culture nor the employee’s characteristics.
Mohammed-Aminu Sanda

Cross-Cultural Competence and Functional Diversity in Business Negotiations: A Developing Country’s Perspective

The paper examines cross-cultural competence and functional diversity in cross border transactions. From the Ghanaian cultural context, we analyse the positions of USA, UK, Germany, Japan, China, and the South African business executives in a buyer-seller relationship exchange of the negotiations using the qualitative exploratory approach. Findings indicate whereas cultural competence significantly affects trans-national negotiation decision making, the success or failure of negotiations is not dependent on the presence of shared cultural identities. Mutual adaptations, trust and power dominance significantly influence cross-border negotiation decision making. Meanwhile, in the buyer-seller dyad, functional diversity in negotiation decision outcomes is influenced by partner’s level of exposure and ethics as openness, integrity, and intrinsically linked to business decisions and contractual agreements.
Anku-Tsede Olivia, Believe Quaqoo Dedzo

Investigation of Cultural Bias Using Physiological Metrics

In today’s world, many business transactions and interactions are conducted cross-culturally. In a business meeting, it is essential avoid a major cultural faux pas in order to not offend your business partners. Individuals must adjust their approach to a situation to create a cultural match. In adjusting this approach, cognitive biases are a potential result in cross-cultural scenarios. We investigate the Mirror Imaging Bias, which was found to be a common result of a shortcut to decide how to act in a situation. Physiological metrics were used to see if biases can be detected in a non-invasive manner. It was found that pupil diameter is a reliable indicator of when Mirror Imaging Bias is present. By understanding how individuals process information and are influenced by Mirror Imaging Bias, we can help create applications as well as provide training to help avoid cultural faux pas.
Renee Rigrish, Mary Fendley

Effects of Price of Zero on Decision Making: An Attempt to Generalize Human’s Irrational Behavior to Price of Zero

When (a − 1)X = Z, the zero-price effect was observed only for (a: large, X: small) and (a: small, X: small). When X was small, the zero-price effect was observed irrespective of the value of a. When X was large, the zero-price effect was not observed. Human behavior tend to deviate from irrational behavior assumed in traditional economics for small values of X irrespective of a. The price of zero must be irrationally chosen due to the overestimation of price of zero. When (a − 1)X > Z, the zero-price effect was observed only for (a: large, X: large) and (a: large, X: small). When a was large, the zero-price effect was observed irrespective of whether X was large or small. When a was small, the zero-price effect was not observed. Human behavior tend to deviate from irrational behavior assumed in traditional economics for large values of a irrespective of the value of a. In this manner, it has been indicated that the zero-price effect is not necessarily observable and holds under limited conditions.
Atsuo Murata, Yasunari Matsushita, Makoto Moriwaka

Human-Machine Interactions and Tools Beyond

Frontmatter

Culture in the Cockpit: Implications for CRM Training

Crew resource management (CRM) is an important airline training tool that was developed in the United States and has been used to train flight crews worldwide since the 1990s. Modern CRM programs cover a wide range of skill areas, including communication, interpersonal skills and decision-making. This paper describes the evolution of CRM and its underlying cultural assumptions. CRM has been criticized for being implicitly biased towards Western culture, and there have been calls for the development of different versions “culturally calibrated” to meet the needs of target participants around the world. This paper reviews research into national cultural differences, as well as airline organizational culture and pilot professional culture, and examines the implications for CRM training. This study is relevant to all international airline flight operations, especially those involving mixed-nationality crews.
Simon Cookson

Irrational Behavior in Adaptation: Difference of Adaptation Process to Comfort and Discomfort Stimulus When Presented All Together or Intermittently

It is generally assumed that the interruption (break) of positive (comfortable) or negative (uncomfortable) experiences disrupt adaptation and consequently intensify the subsequent positive or negative experience. Therefore, it can be speculated that interrupting a consumption experience makes comfortable experiences more delightful and interruption of uncomfortable and painful experience makes this more irritating. This study aimed at verifying this irrational behavior in adaptation process. The comfortable and uncomfortable experiences were an experience of relaxing massage and that of immersing one’s hand in the cold water. It was explored how the interruptive experience of positive (comfortable) or negative (uncomfortable) stimulus disrupt adaptation and intensify subsequent experience as compared with the continuous experience of the same stimuli (experience of the stimulus by bulk). This was investigated as a function of experience time A (comfort stimulus: 300 and 600 s, discomfort stimulus: 50 and 150 s) and duration of interruption B (30, 60, and 90 s for both comfort and discomfort).
Atsuo Murata, Tomoko Nakamura

Foreign Relations: Tools and Analyses

Frontmatter

Evaluating Automatic Learning of Structure for Event Extraction

Analysts engaged in monitoring and forecasting benefit from the structured representations of domain knowledge and societal events that allow for the use of advanced analytics and predictive data models over large amounts of temporally extended data. However, extracting structured data from unstructured data typically requires the development of domain specific software which is costly, takes months to years to create, and cannot adapt to changing domains. In this paper we consider the operational usefulness of an approach pioneered by Chambers and Jurafsky (Template-based information extraction without the templates, 2011, [1]) that performs automatic learning of structured domain knowledge in the form of event templates from unstructured text that are used to automatically extract structured events from text. We generalize this approach and apply it to operationally relevant corpora from Brazil, Mexico, Ukraine, and Pakistan that focus on societal protests and providing aid. We discover that we are able to generate compelling event templates that correspond to event types described by Conflict and Mediation Event Observations (CAMEO) codes (Retrieved from Computational Event Data System, 2014, [2]) which are used to label event types by existing state of the art systems. Additionally, we are able to learn event templates that capture more nuance than the CAMEO codes represent, as well as entirely new and interesting event types. To automate our experimentation, we describe novel automated metrics that allow us to batch run multiple experiments while getting automated feedback on the quality of results from each run. These metrics indicate significant overlap between the events we extract and those extracted by existing systems.
Jason Schlachter, David Van Brackle, Luis Asencios Reynoso, James Starz, Nathanael Chambers

Scenario-Based Practical Exercises to Train and Assess General Cross-Cultural Competence for Special Operations Forces

Our multidisciplinary team designed and developed scenario-based practical exercises (PEs) to train and assess general cross-cultural competence (3C) knowledge and skills. These PEs are consistent with several cultural frameworks and involve the completion of a set of cognitively authentic, mission-centric, increasingly complex scenarios in a mock village with foreign role players. The design of the mock village, scenarios, PEs, and 3C assessment present a set of key features that have contributed to its successful implementation within the context of a general 3C course for Special Operations Forces. Over a dozen classes have completed these scenario-based PEs and the reviews have been consistently positive. Throughout the process, we have incorporated learner feedback to improve the training scenarios and better serve students’ needs. We summarize some of the lessons learned from the design, development, and implementation of the scenario-based PEs to guide the development of future efforts.
Julio C. Mateo, Michael J. McCloskey, Clayton D. Leishman, Marla Federe

Toward Culturally-Aware Systems

Frontmatter

Toward Culturally-Aware, Next Generation Learning Ecosystems

Next generation learning ecosystems will be comprised of intelligent, adaptive environments that utilize one’s cultural footprints to co-create shared narratives and facilitate intercultural understanding. The present paper discusses why digital footprints, cultural signposts, intercultural agents, and transmedia learning are needed to realize relevant learning in virtual environments. The paper introduces notions that may impact the design of culturally-aware information technology for distributed learning are presented.
Elaine M. Raybourn

Investigating Cross-Cultural Differences in Trust Levels of Automotive Automation

Our work examines the levels and perceptions of trust in automotive automation, and the influences of cultural differences concerning trust and automation, with respect to automated automobiles. We found the expected style of communication of the drivers in the autonomous automobile, showed a great effect on trust levels, both at initial contact and with sustained use. This communication style was dependent upon the client culture’s level of context, individualism, and collectivism. Across cultures, the balance of trust levels was found to need to be at moderate levels (not too high or low) to reduce automation misuse, disuse, and abuse. These findings align with the goal to create a positive flow state wherein there are reduced accidents, improved safety and satisfaction with use, across cultures. Future research is needed to assess physiological measures which may be useful to monitor and adapt to the drivers and passengers of automated automobiles.
Valarie A. Yerdon, Tiffani A. Marlowe, William G. Volante, Shuling Li, P. A. Hancock

Evaluating Instructor Configurability for Adaptive Training

Adaptive training technologies offer the promise of more individualized and effective training. However, these technologies increase the complexity of training systems. They also potentially can limit the ability of instructors and curriculum developers without technical skills to customize and to adapt training to specific instructional demands. This paper describes a methodology for verifying that an adaptive training system is configurable and responsive to specifications encoded by instructors. That is, when an instructor desires for the training system to respond in particular ways in particular circumstances, how readily can the adaptive training technology be used to execute that specification? The paper describes a verification methodology and its application to a dynamic adaptation capability in a desktop-based simulation-training prototype.
Robert E. Wray, Angela Woods, Joshua Haley, Jeremiah T. Folsom-Kovarik

Backstory Elaboration: A Method for Creating Realistic and Individually Varied Cultural Avatars

Simulation-based and game-based technology can be used to drive experiential learning of interactive skills such as cross-cultural interactions. Backstory Elaboration (BE) is a method for creating design prompts, dialogs, and interactions that contain realistic verbal behaviors and variability for multiple avatars or non-player characters (NPCs) in cross-cultural virtual training environment. BE structures and simplifies the creation of believable non-player characters with realistic variability with respect to the social-cultural reference. In addition, it articulates easily and effectively with the design and integration of instruction content to support intelligent adaptive tutoring in the learning process. An example application from a clinical communication domain is presented.
Drew A. Zachary, Wayne Zachary, Janis Cannon-Bowers, Thomas Santarelli

The Preference of Using Social Media by Different Attachment Styles for Managing Romantic Relation

This research is mainly focus on the discussion of the user experience and preference for college students with their romantic relation partner. Nowadays, people always use social media to contact with other people, especially their romantic partner. Couples use social media to chat every moment when they miss their lover and also share their life by sending photos. By attachment theory, there are four different attachment styles. Each attachment style is measured by avoidance and anxiety. Previous studies have investigated the effect of attachment theory in romantic relation. However, seldom studies discuss the use of social media between romantic partners. We want to know that whether the social media used by different attachment style people would influence the satisfaction of love or not.
Wen-Chien Lin, Yu-Chen Hsu

Contemporary Defense Applications of Social Science

Frontmatter

Considering Culture in Contemporary Military Interventions: Simulating the Effects of Actions of Influence on a Civilian Population

As armed conflicts of today are highly population-centric, a national or international military force deployed to enforce a peacebuilding agenda has necessarily to face a multifaceted and complex local culture. To meet such a challenging intercultural situation, soldiers nowadays implement actions of influence. These are non-kinetic operations aiming at shaping attitudes and behaviors and gain legitimacy and support. Understanding how local cultural norms and values can affect the outcome of such courses of action is of great importance if success is to be achieved, soldiers have therefore to be trained in this domain. The purpose of the SICOMORES system is to meet this need by modeling a wide range of these actions: psychological operations (PsyOps), key leader engagements (KLE) and civil-military cooperation actions (CIMIC). They are discrete events whose effects are simulated in a multilayered networked population of individual cognitive agents characterized by cultural features.
Bergier Jean-Yves, Colette Faucher

Development of a Competency Model for Civil-Military Teaming

The nature and complexities of today’s military operations are such that no single organization, department, or agency has all the requisite resources, authority, or expertise to single-handedly provide an effective response. These operations require civil-military teaming to establish, manage, and participate in collaborations among various military, governmental, non-governmental, local national leadership, and civilian agencies. This research was conducted to develop requirements for successful teaming performance. An initial competency model, developed from a domain analysis, was validated through 19 interviews with participants from the U.S. Army, the State Department, USAID, USDA and other organizations. Results suggest a competency model with three higher-order meta-competencies and 12 lower level competencies. Thirty-two specific decision points that present significant performance challenges are also described and linked to tasks and activities. The resulting decision requirements provide context for potential training objectives and scenarios to identify and address gaps in existing training and education.
Karol G. Ross, Michelle Wisecarver, Carol A. Thornson, Deborah A. Peluso, Melinda Key-Roberts

A Planning Tool for Interaction with Influential Actors Based on Paraconsistent Logic

Interaction with influential actors is essential during international operations. Currently, however, commanders only have little support, if any, for planning and performing these interactions besides their own understanding of the situation. Since there are inherent conflicts among actors, a planning tool is presented that use paraconsistent belief integration to guide analysts’ attention towards actors’ relations, beliefs, and group identification modes, which may be important to consider when planning the interaction. The planning tool is evaluated in a representative scenario where analysts have to find ways and means to disrupt a drug trade between irregular and criminal actors. The available information enables the analyst to identify likely suspects in the drug trade, identify actors that have interests that are aligned the international force, as well as important considerations for planning the interaction with these actors. Preliminary evaluations show that better planning tools are very desirable for commanders and intelligence officers.
Peter Svenmarck, Eric Sjöberg, Christophe Fagot

The Effects of Demographic and Sociocultural Variables on 3rd Year ROTC Cadets Officer/Evaluator Rating Scores

We examined the effectiveness of several pre-exercise measures to both observe relationships among these variables and to attempt to predict 3rd year ROTC Cadet officer/evaluator report (OER) scores, a strong indication of a cadet’s leadership and decision-making capability. Participants consisted of a sample of 16 (13 male and 3 female) cadets from both the University of Virginia and Liberty University whose ages ranged from 19 to 24 years (mean = 20.7). Significant correlation relationships were revealed. A multiple regression model yielded strong evidence that demographic and 3CI scores were predictive of OER scores attained at Fort Knox. Correlations revealed multiple significant relationships leading to the suggestion that many mediating relationships existed within the variable relationship structure.
David R. Scribner

Sociocultural, Behavioral Modeling for Defense Applications: Theory and Practice

Frontmatter

The Conundrum of Verification and Validation of Social Science-Based Models Redux

In systems engineering, the definitions of “verification” and “validation” are settled; consistent with the US Department of Defense’s (Department of Defense, [1]) definitions; and distinct from one another. This distinction blurs in the V&V of social science-based models. Unlike physics-based models, the theoretical underpinnings of social science models are not readily verified through observation of real-world events or empirical testing. Hence, they are often contested. When experts do not agree on what the right thing to do is, determining that the model is built right (verification) and that the right thing has been built (validation) cannot be separated (Verification as a form of validation: deepening theory to broaden application of dod protocols to the social sciences, [2]). This paper updates an earlier one (The conundrum of verification and validation of social science-based models, [3]), that reviewed the literature on V&V of models and outlined future directions, and describes the experiences LANL researchers have had with the V&V of extensible logic models (https://www.orau.gov/dhssummit/2009/presentations/march18/plenary/shevitz_mar18.pdf, [4]) used to evaluate the efficacy of various technologies in countering national security threats.
Heidi Ann Hahn

Socio-cultural Modeling and Dynamic Decision Making

In the field of Cross-Cultural Decision Making, our work is oriented towards supporting decision making process by providing a dynamic and interactive visualisation interface. The idea with this approach is that users should be able to explore a problem space using visualisation that facilitate quick perceptions and understanding. Vesta-Cosy application, developed in the frame of a research project, therefore combines paraconsistent reasoning and works on graphic semiology. We first present the currently used approaches of decision making in Vesta Cosy. Thereafter, the Vesta Cosy application is described in details, especially the different models and their connection with visual and algorithmic units. We also present the theoretical framework which we use for a specific use case scenario. This theoretical framework aims at enabling the consideration of socio-cultural factors in Decision Making.
Orélie Desfriches Doria, Peter Svenmarck, Christophe Fagot

Examining the, Ideological, Sociopolitical, and Contextual Factors Underlying the Appeal of Extremism

This paper discusses and seeks to synthesize theories regarding the role of ideology and psychosocial contextual factors in shaping motivations and behaviors of individuals within violent extremist movements. To better understand how these factors give birth to and nurture extremist social movements, theory from a multitude of disciplines was incorporated into a conceptual model of the drivers associated with terrorist behaviors. This model draws upon empirically supported theoretical notions, such as the violation of socioeconomic and geopolitical expectations, the concept of perceived threat, one’s mental construction of the world and group polarization. It also draws upon the importance of one’s social identity, sense of belonging, and the perceived “glamour” associated with extremist group behaviors.
Grace-Rose Williams, Michael L. Bernard, Robert F. Jeffers

Using Computational Modeling to Examine Shifts Towards Extremist Behaviors in European Diaspora Communities

We created a simulation model to investigate potential links between the actions of violent extremist organizations (VEOs), people in the VEO’s home country, and diaspora communities from that country living in the West. We created this model using the DYMATICA framework, which uses a hybrid cognitive-system dynamics modeling strategy to simulate behaviors based on psycho-social theory. Initial results of the model are given, focusing on increases to VEO funding and recruiting resulting from an invasion of the VEO’s home country. Western intervention, prejudice, and economic drivers are also considered.
Asmeret Bier Naugle, Michael L. Bernard

A Statistical Approach to the Subnational Geolocation of Event Data

Geolocation is the identification of the real-world geographic location of items such as coded news events. We have developed software to geolocate high volumes of event data, often to the subnational level, by combining existing entity extraction technologies with new statistical ranking algorithms. Our three-stage pipeline consists of: (1) named-entity recognition (identifying the text strings that represent named entities from underlying text and classifying them by type); (2) entity resolution (matching location strings to specific real-world locations referenced in a gazetteer); and, (3) location determination (selecting the most appropriate location for the event). We have used this software operationally to geolocate tens of millions of events and have formally evaluated both the accuracy and specificity of our results. Our latest formal evaluation had an overall subnational accuracy of 78 %, with 85 % of all events geolocated at a subnational level.
Jennifer Lautenschlager, James Starz, Ian Warfield

Tweet Sentiment Analysis with Pronoun Choice Reveals Online Community Dynamics in Response to Crisis Events

We describe the emergence of an online community from naturally occurring social media data. Our method uses patterns of word choice in an online social platform to characterize how a community forms in response to adverse events such as a terrorist attack. Our focus is English Twitter messages after the Charlie Hebdo terrorist attack in Paris in January 2015). We examined the text to find lexical variation associated with measures of valence, arousal and concreteness. We also examine the patterns of language use of the most prolific twitter users (top 2 % by number of tweets) and the most frequent tweets in our collection (top 2 % by number of retweets). Differences between users and tweets based on frequency are revealing about how lexical variation in tweeting behavior reflects evolution of a community in reaction to crisis events on an international scale.
Samira Shaikh, Laurie Beth Feldman, Eliza Barach, Yousri Marzouki
Weitere Informationen

Premium Partner

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.

Whitepaper

- ANZEIGE -

Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!

Bildnachweise