Unifying Algorithmic and Theoretical Perspectives: Emotions in Online Reviews and Sales

2023 | Management Information Systems Quarterly | Citations: 2

Authors: Yu, Yifan; Yang, Yang; Huang, Jinghua; Tan, Yong

Abstract: Emotion artificial intelligence, the algorithm that recognizes and interprets v ... Expand

Abstract: Emotion artificial intelligence, the algorithm that recognizes and interprets various human emotions beyond valence (positive and negative polarity), is still in its infancy but has attracted attention from industry and academia. Based on discrete emotion theory and statistical language modeling, this work proposes an algorithm to enable automatic domain-adaptive emotion lexicon construction and multidimensional emotion detection in texts. Using a large-scale dataset of China's movie market from 2012 to 2018, we constructed and validated a domain-specific emotion lexicon and demonstrated the predictive power of eight discrete emotions (i.e., surprise, joy, anticipation, love, anxiety, sadness, anger, and disgust) in online reviews on box office sales. We found that representing overall emotions through discrete emotions yields higher prediction accuracy than valence or latent emotion variables generated by topic modeling. To understand the source of the predictive power from a theoretical perspective and to test the cross-culture generalizability of our prediction study, we further conducted an experiment in the U.S. movie market based on theories on emotion, judgment, and decision-making. We found that discrete emotions, mediated by perceived processing fluency, significantly affect the perceived review helpfulness, which further influences purchase intention. Our work shows the economic value of emotions in online reviews, generates insight into the mechanism of their effects, and has managerial implications for online review platform design, movie marketing, and cinema operations. Collapse

Topics: online review Python user-generated content microblog marketing management

Methods: computational algorithm word2vec parametric test product review experiment

Theories: psychological theory

The Influence of Health Data on the Use of the Electronic Health Record (EHR) – a Mixed Methods Approach

2023 | Americas Conference on Information Systems | Citations: 0

Authors: von Kalckreuth, Niklas; Prümper, Alina; Feufel, Markus

Abstract: The use of electronic health records (EHRs) offers many benefits, but users are ... Expand

Abstract: The use of electronic health records (EHRs) offers many benefits, but users are also critical of them because of concerns about privacy and the sensitivity of health data. Given the ambiguity of data sensitivity, we examine which characteristics of health data influence users' upload behavior, and which are perceived as sensitive. A semi-structured interview (N=30) was conducted to locate characteristics of health data, which influence the user's upload behavior. These characteristics were then empirically evaluated in a user study (N=50). The complexity of diseases and their stigmatization potential are characteristics which influence the uploading behavior. We verify empirically that the uploading of health data is rejected when there is a high potential for stigmatization, while it is accepted when the complexity of the disease increases. Health data are considered by users to have different sensitivities, relative to stigmatization potential. Privacy Calculus regarding EHRs should consider these characteristics of health data. Collapse

Topics: healthcare data mobile application information privacy concern usage intention mobile health

Methods: experiment qualitative interview personal interview survey binomial logistic regression

Theories: privacy calculus theory

CONTINUOUS IMPROVEMENTS: HOW USERS PERCEIVE UPDATES

2019 | European Conference On Information Systems | Citations: 0

Authors: Franzmann, Daniel; Wiewiorra, Lukas; Holten, Roland

Abstract: Software updates are an instrument commonly used in software development project ... Expand

Abstract: Software updates are an instrument commonly used in software development projects to modify or enhance the functionalities of the underlying base-software. They can change or add features, fix critical bugs or close security vulnerabilities. We present the results of an online-vignette experiment with 322 participants to test the effect of three different software update types on users. This research paper uses the post-adoption IS continuance model (ISCM) as a theoretical lens, and we compare pre- and posttreatment measurements across our several experimental groups, namely feature updates, bug fix updates, and security updates. Our results suggest that non-feature updates, such as a bug fix update can also have a positive effect on users’ perception of the underlying base-software and specifically on the variables used in the ISCM. Furthermore, we try to shed light on a discrepancy found in recent IS literature regarding the effects of security updates. Our findings extend the theoretical conceptualization of software updates, enhance the understanding of how they affect users, and provide guidance to developers and publishers in the design and alignment of their software development projects. Collapse

Topics: perceived usefulness system maintenance affordance IT security threat systems development

Methods: experimental group experiment survey literature study experimental design

Theories: information systems theory

Q&As and Reviews: Substitutes or Complements?

2018 | Americas Conference on Information Systems | Citations: 0

Authors: Jetley, Gaurav; Shivendu, Shivendu

Abstract: Reviews are a major source of post-purchase experiences and have a significant e ... Expand

Abstract: Reviews are a major source of post-purchase experiences and have a significant effect on consumer decision making but lack prospective consumer-to-past consumer interaction. QAs facilitates this interaction and provides ability to ask specific pre-purchase questions, and therefore, fills in the informational gaps in the online review systems. However, it’s not clear if the information contained in reviews and QAs is same or different. To answer this key question, we study the complementary and substitute informational content in reviews and QAs for different types of products. We employ a novel method by using measures borrowed from information and measure theory and using topic modeling technique of LDA and find that for high involvement product categories, the reviews and QAs complement each other by providing information on segregated thematic content. For low involvement products, we find that both reviews and QAs contain similar thematic content and might act as substitutes. Collapse

Topics: laptop computer word of mouth online word of mouth user-generated content decision making

Methods: topic model natural language processing latent dirichlet allocation survey generalized linear model

Theories: information theory

Explicitness of Consequence Information in Privacy Warnings: Experimentally Investigating the Effects on Perceived Risk, Trust, and Privacy Information Quality

2014 | International Conference on Information Systems | Citations: 0

Authors: Bal, Gökhan

Abstract: Utility that modern smartphone technology provides to individuals is most often ... Expand

Abstract: Utility that modern smartphone technology provides to individuals is most often enabled by technical capabilities that are privacy-affecting by nature, i.e. smartphone apps are provided with access to a multiplicity of sensitive resources required to implement context-sensitivity or personalization. Due to the ineffectiveness of current privacy risk communication methods applied in smartphone ecosystems, individuals’ risk assessments are biased and accompanied with uncertainty regarding the potential privacy-related consequences of long-term app usage. Warning theory suggests that an explicit communication of potential consequences can reduce uncertainty and enable individuals to make better-informed cost-benefit trade-off decisions. We extend this design theory to the field of information privacy warning design by experimentally investigating the effects of explicitness in privacy warnings on individuals’ perceived risk and trustworthiness of smartphone apps. Our results suggest that explicitness leads to more accurate risk and trust perceptions and provides an improved foundation for informed decision-making. Collapse

Topics: privacy mobile application smartphone mobile application market privacy behavior

Methods: experimental group experiment nonparametric test Mann Whitney U test statistical hypothesis test

Not Just for Support: Companionship Activities in Healthcare Virtual Support Communities

2014 | Communications of the Association for Information Systems | Citations: 6

Authors: Huang, Kuang-Yuan; Chengalur-Smith, InduShobha; Ran, Weijia

Abstract: The phenomenon of social support-aid and assistance exchanged through social re ... Expand

Abstract: The phenomenon of social support-aid and assistance exchanged through social relationships and interpersonal transactions-has been studied extensively for decades. In the context of healthcare virtual support communities, researchers have focused on exploring community members' support behavior and its effects on individuals' health outcomes. This emphasis, however, has led to the neglect of another type of social interaction that also promotes individual health-companionship activities. We argue that in order to gain a deeper insight into the online support phenomenon, the consideration of companionship activities, in addition to social support exchange, is necessary. To bridge this gap in the literature, this article attempts to contrast community members' support behavior and companionship activities in two large healthcare virtual support communities -one for patients w ith breast cancer and the other for patients with prostate cancer. Based on the identi fication of the two types of social activities from the two cancer support communities, the relationship between individuals' participation in these activities, and gender differences in their activity engagement are also hypothesi zed and tested. Our goal is to advance the understanding of online socio-behavioral dynamics of virtual support communities. We al so wi sh to provide insights into the design of such communities and the delivery of patient-focused healthcare interventions. Collapse

Topics: social network online community internet technology information exchange problem solving

Methods: qualitative content analysis descriptive statistic social network analysis nonparametric test statistical hypothesis test

What Drives Users’ Website Registration? A Randomized Field Experiment

2013 | International Conference on Information Systems | Citations: 0

Authors: Li, Ting; Pavlou, Paul

Abstract: User registration is an important prerequisite for the success of many websites ... Expand

Abstract: User registration is an important prerequisite for the success of many websites by enabling users to gain access to domain information and often personalized content. It is not always desirable for users, however, because they need to disclose personal information. This paper examines what drives user registration. The results show that brand awareness is an important determinant of user registration by negatively moderating (attenuating) the negative effect of information privacy concerns on user registration and positively moderating (reinforcing) the positive effect of trust on user registration. Furthermore, to alleviate information privacy concerns and build trust in the website, we conducted a randomized field experiment and empirically examined the effectiveness of advertising two types of information, i.e., word-of-mouth information and popularity information, and measured their economic value. Interestingly, when both types of information are shown, the website achieved over 12% higher conversion rate than without any information. Collapse

Topics: website information privacy concern advertising management privacy internet technology

Methods: survey experiment field experiment descriptive statistic parametric test

Organizational Characteristics and their Influence on Information Security in Trinidad and Tobago

2013 | Americas Conference on Information Systems | Citations: 0

Authors: Papin-Ramcharan, Kyle; Fraser, Simon

Abstract: This paper investigates the effect of organizational characteristics on informat ... Expand

Abstract: This paper investigates the effect of organizational characteristics on information security practices in Trinidad and Tobago. As a theoretical lens, this study relies on a hypothesized model derived from Chang and Wang (2010) to test 24 hypotheses relating to information security practices. The data was collected using online surveys and was analyzed using factor analysis and structured equation modeling (SEM). Upon final analysis, 8 of the 24 hypotheses were confirmed. Collapse

Topics: data security IT skill enterprise architecture information security practice IS management

Methods: survey data transformation structural equation modeling chi squared test factor analysis

Knowing What a User Likes: A Design Science Approach to Interfaces That Automatically Adapt to Culture

2013 | Management Information Systems Quarterly | Citations: 51

Authors: Reinecke, Katharina; Bernstein, Abraham

Abstract: Adapting user interfaces to a user's cultural background can increase satisfacti ... Expand

Abstract: Adapting user interfaces to a user's cultural background can increase satisfaction, revenue, and market share. Conventional approaches to catering for culture are restricted to adaptations for specific countries and modify only a limited number of interface components, such as the language or date and time formats. We argue that a more comprehensive personalization of interfaces to cultural background is needed to appeal to users in expanding markets. This paper introduces a low-cost, yet efficient method to achieve this goal: cultural adaptivity. Culturally adaptive interfaces are able to adapt their look and feel to suit visual preferences. In a design science approach, we have developed a number of artifacts that support cultural adaptivity, including a prototype web application. We evaluate the efficacy of the prototype's automatically generated interfaces by comparing them with the preferred interfaces of 105 Rwandan, Swiss, Thai, and multicultural users. The findings demonstrate the feasibility of providing users with interfaces that correspond to their cultural preferences in a novel yet effective manner. Collapse

Topics: national culture user interface usability knowledge representation web application

Methods: experiment design artifact ontological modelling computational algorithm design science

Theories: cultural dimensions theory

Conceptualizing E-Inclusion in Europe: An Explanatory Study

2012 | Information Systems Management | Citations: 0

Authors: Weerakkody, Vishanth; Dwivedi, Yogesh K.; El-Haddadeh, Ramzi; Almuwil, Ahlam; Ghoneim, Ahmad

Abstract: The aim of this article is to conceptualize e-Inclusion and identify factors aff ... Expand

Abstract: The aim of this article is to conceptualize e-Inclusion and identify factors affecting it. A critical review of the literature is conducted to identify and categorize the factors influencing e-Inclusion into a comprehensive taxonomy. Using a survey questionnaire, the impact of these factors in influencing citizens' adoption of e-government services was examined. The findings highlight a number of factors under demographic, political, economic social, cultural, and infrastructural dimensions that can have a significant influence on e-Inclusion. Collapse

Topics: government system internet technology legal context digital divide electronic commerce

Methods: survey Pearson's Chi square test literature study chi squared test synthesis