From Groups to Communities: A Resource Mobilization Theory Perspective on the Emergence of Communities

2023 | Information Systems Frontiers | Citations: 1

Authors: Angelopoulos, Spyros; Canhilal, Kubra S.; Hawkins, Matthew A.

Abstract: Groups and communities have been key topics in the information systems (IS) rese ... Expand

Abstract: Groups and communities have been key topics in the information systems (IS) research agenda. While communities are assumed to emerge at the intersection of overlapping groups and their practices, prior research has mainly focused on their dynamics and evolution. This has resulted to limited empirical support regarding the emergence of communities. We address that lacuna by tracing the emergence of communities through the prism of resource mobilization theory. In doing so, we make use of a unique longitudinal dataset and incorporate Topic Modelling, Bipartite Network Analysis, and Community Detection. We show that new communities are formed at the intersection of overlapping groups and practices. In addition, we contribute to the IS literature by demonstrating that their emergence occurs due to resource mobilization that gives rise to a shared mindset. We also reveal that multiple resources are incorporated into the practices of an emerging community. By combining large datasets and innovative computational approaches, we help IS theory and practice to move away from traditional "what" questions towards the more insightful "how" ones. We discuss the theoretical and practical implications of our work and delineate an agenda for future research on the topic. Collapse

Topics: accounting identity theft database system

Methods: longitudinal research theoretical contribution theory development network analysis topic model

Theories: information systems theory

ChatGPT and GPTZero in Research and Social Media: A Sentiment- and Topic-based Analysis

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Heumann, Maximilian; Kraschewski, Tobias; Breitner, Michael H.

Abstract: Conversational AI agents like ChatGPT have gained considerable attention in rec ... Expand

Abstract: Conversational AI agents like ChatGPT have gained considerable attention in recent years, with potential implications across various domains. However, there is a gap in understanding the prevailing opinions, topics, and concerns of the public and research communities regarding these technologies. This study conducts a semi-automated analysis of over 1,006,000 tweets and 279 scholarly articles to explore perspectives on ChatGPT and its potential misuse for plagiarism, as well as the comparatively lower interest in GPTZero, a technology designed to counter AI-driven plagiarism. Employing advanced natural language processing techniques, such as sentiment analysis and topic modeling, we identify challenges and opportunities related to ChatGPT and GPTZero. Our findings uncover potential areas for improvement and provide guidance for future research and development in the field of conversational AI. Collapse

Topics: Twitter artificial intelligence human computer interaction usability Python

Methods: chatGPT topic model chatbot sentiment analysis natural language processing

Fun Shopping: A Randomized Field Experiment on Gamification

2023 | Information Systems Research | Citations: 0

Authors: Ho, Yi-Jen (Ian); Liu, Siyuan; Wang, Lei

Abstract: Gamification utilizes game-like features to engage participants, widely implemen ... Expand

Abstract: Gamification utilizes game-like features to engage participants, widely implemented in a variety of contexts. Such an IT-enabled engagement strategy serves as a marketing device to boost sales and customer loyalty. This study focuses on two significant game elements (i.e., badges and leaderboards) that promote consumer motivations and social comparisons. To qualify the impacts, we conduct a randomized field experiment at one of the largest shopping malls in Asia. In the experiment, we contrast the two elements against coupons regarding various shopping outcomes. A two-period design (consisting of the treatment and posttreatment periods) identifies the long-term behavior changes after the treatment removals. The main results suggest that badging and leaderboarding promote sales by 21.5% and 22.5% in the treatment period, respectively, whereas couponing delivers a more potent effect of 31.7%. In the posttreatment period, the gamification impacts remain significant compared with the baseline, but the influence of couponing fades out. Besides, the additional analyses document the salient heterogeneous treatment effects across demographics. We further discover the substantial differences in the within-group heterogeneity across the treatments. Specifically, badging is a balanced tool for attracting the general public, whereas leaderboarding is a double-edged sword that could encourage self-reinforcing or self-banishing. Finally, gamification brings more explorations that lead to additional sales and engagements. Overall, the robust results can be translated into actionable strategies to utilize gamification proactively.History: Ravi Bapna, Senior Editor; Yili (Kevin) Hong, Associate Editor. Collapse

Topics: gamification wireless LAN consumer behavior technology adoption user interface

Methods: experiment experimental group survey randomized field experiment parametric test

Theories: motivation theory self determination theory

A novel label-based multimodal topic model for social media analysis

2023 | Decision Support Systems | Citations: 0

Authors: Li, Hao; Qian, Yang; Jiang, Yuanchun; Liu, Yezheng; Zhou, Fan

Abstract: Extracting useful knowledge from multimodal data is the core of many multimedia ... Expand

Abstract: Extracting useful knowledge from multimodal data is the core of many multimedia applications, such as recommendation systems, and cross-modal retrieval. In this paper, we propose a label-based multimodal topic (LB-MMT) model to jointly model text and image data tagged with multiple labels. Specifically, we use the labels as supervised information to generate the text and image data. In the LB-MMT model, we assume that the textual words and visual words related to each text and image are drawn from a mixture of latent topics, where each topic is represented as a group of textual words and visual words. Moreover, we introduce multiple topics for each label, to build the top-down relationship from label to text and image. To investigate the effectiveness of the proposed approach, we conduct extensive experiments on a real-world multimodal dataset with labels. The re­ sults show the proposed approach obtains superior performances on topic coherence and label prediction compared with previous competitors. In addition, we show that our model yields interesting insights about multimodal topics. The proposed model provides important practical implications, e.g., designing more attrac­ tive multimodal contents for marketers. Collapse

Topics: Java social media Linux electronic commerce search engine

Methods: topic model word embedding Gibbs sampling BERT computational algorithm

Theories: technology acceptance model

Corporate Social Responsibility Consistency: Moral Sensemaking from Top Management Team to Online Social Media

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Luo, Yuxiao; Peifer, Jared; Huang, Linmei

Abstract: Drawing on organization character theory and corporate social responsibility (C ... Expand

Abstract: Drawing on organization character theory and corporate social responsibility (CSR) sensemaking, this study explores the CSR consistency of moral sensemaking in the company from top management to social media communication channels. First, we measure CSR moral sensemaking in top management team (TMT) letters and firm-generated content (FGC) on social media platform based on the dictionary developed from qualitative content analysis, topic modeling, and CSR expert rating. Second, we compare the moral sensemaking between two communication channels. Third, we investigate the relationship between moral sensemaking consistency and CSR engagement of the company. Our results contribute to the literature in business ethics, management, and social media research in IS. The study will also offer an alternative way for CSR evaluation and bring practical implications to CSR investors and rating agencies. Collapse

Topics: sensemaking social media Twitter financial performance website

Methods: qualitative content analysis topic model statistical hypothesis test longitudinal research mixed method

Why some products compete and others don't: A competitive attribution model from customer perspective

2023 | Decision Support Systems | Citations: 0

Authors: Qian, Yang; Jiang, Yuanchun; Shang, Jennifer; Chai, Yidong; Liu, Yezheng

Abstract: Competitive intelligence uses information collected about competitors to derive ... Expand

Abstract: Competitive intelligence uses information collected about competitors to derive better managerial insights. In this study, we focus on identifying the competitors and detecting the competitive dimensions concurrently. To achieve this goal, we propose an aspect-level competitive attribution model (a variation of the topic model) to leverage consumer-reviewed products and their review texts. To better analyze product relations and the un­ derlying competitive aspects, we consider consumer limited attention when modeling consumers' preferences and introduce a background aspect to filter out the trivial and maintain the valuable competition-related in­ formation in review texts. We validate this approach using a dataset of 785 products reviewed by 15,669 con­ sumers in the auto industry. Based on the empirical experiments, we show that our model can accurately infer high-quality competitive segments and decipher competition-related aspects corresponding to these segments. To highlight differences, we conduct comparisons and find our approach outperforms the benchmark models meaningfully in the literature when predicting consumers' online behaviors. Collapse

Topics: online review competitive intelligence marketing management competitive advantage user-generated content

Methods: topic model experiment Gibbs sampling natural language processing computational algorithm

Exploiting Connections among Personality, Job Position, and Work Behavior: Evidence from Joint Bayesian Learning

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Shen, Dazhong; Zhu, Hengshu; Xiao, Keli; Zhang, Xi; Xiong, Hui

Abstract: Personality has been considered as a driving factor for work engagement, which s ... Expand

Abstract: Personality has been considered as a driving factor for work engagement, which significantly affects people’s role performance at work. Although existing research has provided some intuitive understanding of the connection between personality traits and employees’ work behaviors, it still lacks effective quantitative tools for modeling personality traits, job position characteristics, and employee work behaviors simultaneously. To this end, in this article, we introduce a data-driven joint Bayesian learning approach, Joint-PJB, to discover explainable joint patterns from massive personality and job-position-related behavioral data. Specifically, Joint-PJB is designed with the knowledgeable guidance of the four-quadrant behavioral model, namely, DISC (Dominance, Influence, Steadiness, Conscientiousness). Based on the real-world data collected from a high-tech company, Joint-PJB aims to highlight personality-job-behavior joint patterns from personality traits, job responsibilities, and work behaviors. The model can measure the matching degree between employees and their work behaviors given their personality and job position characteristics. We find a significant negative correlation between this matching degree and employee turnover intention. Moreover, we also showcase how the identified patterns can be utilized to support real-world talent management decisions. Both case studies and quantitative experiments verify the effectiveness of Joint-PJB for understanding people’s personality traits in different job contexts and their impact on work behaviors. Collapse

Topics: personality IT personell turnover IT job missing data decision making

Methods: experiment artificial neural network survey topic model case study

Combating Loneliness with Artificial Intelligence: An AI-Based Emotional Support Model

2023 | HICSS | Citations: 0

Authors: Sullivan, Yulia; Nyawa, Serge; Fosso Wamba, Samuel

Abstract: Artificial intelligence (AI)-based systems, such as AI companions, have been inc ... Expand

Abstract: Artificial intelligence (AI)-based systems, such as AI companions, have been increasingly used to meet the needs of individuals who experience loneliness. In this current study, we sought to identify the mechanism underlying human-AI interactions in the mental health context. We use a Latent Dirichlet Allocation (LDA) approach to analyze a sample of user-generated content consisting of rich data on AI companion app’s reviews over a two-year period. We extracted five positive topics (i.e., perceived humanness, perceived emotional support, perceived AI’s friendship, perceived (less) loneliness, and mental health benefits) and four negative topics (i.e., perceived lack of conscientiousness, perceived incredibility, perceived violation of privacy, and perceived creepiness of AI) from our analysis. Our AI-based emotional support model suggests that these positive and negative characteristics are interrelated. Our study provides an understanding of the relationship between AI companions and human users in light of research showing the effectiveness of an AI-based intervention for mental health care. Collapse

Topics: artificial intelligence human AI collaboration privacy user-generated content mobile application

Methods: natural language processing machine learning latent dirichlet allocation hierarchical clustering topic model

Theories: uncanny valley theory

Software Components and Product Variety in a Platform Ecosystem: A Dynamic Network Analysis of WordPress

2023 | Information Systems Research | Citations: 0

Authors: Um, Sungyong; Zhang, Bin; Wattal, Sunil; Yoo, Youngjin

Abstract: Software components, such as application programming interfaces (APIs), provided ... Expand

Abstract: Software components, such as application programming interfaces (APIs), provided by both the platform owner and external developers in a platform ecosystem are vital to online digital platforms. These APIs are associated with functionality provided by the platform. A larger number of APIs used is generally associated with an increase in the platform ecosystem’s variety of products. However, the precise nature of the relationship between the use of APIs and product variety in a platform ecosystem is not yet known because of the lack of appropriate methodologies to analyze the complex data generated in such platform ecosystems. Drawing on a recombinatorial design perspective, we use a dynamic network model to create metrics for product variety in a digital ecosystem and study how the use of different types of APIs affects product variety. In particular, we theorize that, contrary to existing models, the structure of APIs in a large platform ecosystem is not limited to a core–periphery structure, but includes an additional third layer that we refer to as the regular core. We further hypothesize that external APIs in the regular core play a crucial role in increasing product variety in the ecosystem. To test our hypothesis, we conduct an empirical study using longitudinal data of all available digital product (i.e., plug-in) source codes on WordPress.org, the world’s largest content management system and one of the most extensive digital platform ecosystems. By analyzing all of the plug-ins on WordPress over 10 years from its inception, we find the support of our three-layer structure of APIs in a platform ecosystem: complete core, regular core, and periphery. Our empirical analysis further supports the role of external APIs in the regular core in increasing product variety. We, however, find that the strength of this effect diminishes in a newly created product category. History: Param Singh, Senior Editor; Pallab Sanyal, Associate Editor. Funding: This work was supported by the Ministry of Education Singapore [Grants R-253-000-122-133 and T1-251RES1916], the National Science Foundation [Grants 1261977 and 1120966], and Club Informatique des Grandes Entreprises Françaises. Supplemental Material: The e-companion is available at https://doi.org/10.1287/isre.2022.1172. Collapse

Topics: application programming interface digital ecosystem digital product innovation management website

Methods: doc2vec hierarchical clustering longitudinal research cluster analysis chi squared test

Getting Personal: A Deep Learning Artifact for Text-Based Measurement of Personality

2023 | Information Systems Research | Citations: 0

Authors: Yang, Kai; Lau, Raymond Y. K.; Abbasi, Ahmed

Abstract: Analysts, managers, and policymakers are interested in predictive analytics capa ... Expand

Abstract: Analysts, managers, and policymakers are interested in predictive analytics capable of offering better foresight. It is generally accepted that in forecasting scenarios involving organizational policies or consumer decision making, personal characteristics, including personality, may be an important predictor of downstream outcomes. The inclusion of personality features in forecasting models has been hindered by the fact that traditional measurement mechanisms are often infeasible. Text-based personality detection has garnered attention because of the public availability of digital textual traces. However, the text machine learning space has bifurcated into two branches: feature-based methods relying on manually crafted human intuition, or deep learning language models that leverage big data and compute, the main commonality being that neither branch generates accurate personality assessments, thereby making personality measures infeasible for downstream forecasting applications. In this study, we propose DeepPerson, a design artifact for text-based personality detection that bridges these two branches by leveraging concepts from relevant psycholinguistic theories in conjunction with advanced deep learning strategies. DeepPerson incorporates novel transfer learning and hierarchical attention network methods that use psychological concepts and data augmentation in conjunction with person-level linguistic information. We evaluate the utility of the proposed artifact using an extensive design evaluation on three personality data sets in comparison with state-of-the-art methods proposed in academia and industry. DeepPerson can improve detection of personality dimensions by 10–20 percentage points relative to the best comparison methods. Using case studies in the finance and health domains, we show that more accurate text-based personality detection can translate into significant improvements in downstream applications such as forecasting future firm performance or predicting pandemic infection rates. Our findings have important implications for research at the intersection of design and data science, and practical implications for managers focused on enabling, producing, or consuming predictive analytics.History: Olivia Sheng, Senior Editor; Huimin Zhao, Associate Editor.Funding: This work was supported by Oracle for Research (NLP for the Greater Good) and the U.S. National Science Foundation’s Division of Information and Intelligent Systems [Grants BDS-1636933 and IIS-1816504]. The work was also partly supported by the Research Grants Council of the Hong Kong Special Administrative Region [Project: CityU 11507219] and the City University of Hong Kong SRG [Project: 7005780].Supplemental Material: The online appendices are available at https://doi.org/10.1287/isre.2022.1111. Collapse

Topics: personality Twitter social media pandemic Google+

Methods: machine learning BERT design science deep learning computational algorithm

Theories: big five model