Save Our Souls: Study of Twitter Use during India’s COVID-19 Pandemic

2023 | International Conference on Information Systems | Citations: 0

Authors: Bhattacharyya, Samadrita; Mojumder, Probal

Abstract: Twitter is a commonly used social platform for communication during disasters. ... Expand

Abstract: Twitter is a commonly used social platform for communication during disasters. Tweets by citizens during disasters to share information, seek, and offer help create a body of spontaneous, decentralized, emergent social media communication. Users' exploit Twitter's reach-enabling technological functionalities (hashtags (#), mentions (@), and 'reply-to') to draw attention to the messages. Set in context of the second wave of COVID-19 in India, that saw a surge in citizen-driven tweets seeking healthcare resources from fellow citizens and officials (i.e., SOS tweets), our paper empirically analyses the effects of Twitter's reach-enabling functionalities on online responses (i.e., retweets and replies) to these SOS tweets. We investigate the effects of inclusion of hashtags, mentions, and 'reply to' SOS tweets. We also examine the moderating effect of how the effects of the reach-enabling functionalities change as the social platform gets crowded with SOS tweets. The study offers various academic and practical implications. Collapse

Topics: Twitter pandemic social media Python societal evaluation criteria

Methods: propensity score method machine learning propensity score matching econometric modeling robustness check

Economic Impacts of Platform-Endorsed Quality Certification: Evidence from Airbnb

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Dewan, Sanjeev; Kim, Jooho; Nian, Tingting

Abstract: We contribute to the emerging literature on quality certification by digital pl ... Expand

Abstract: We contribute to the emerging literature on quality certification by digital platforms by studying the launch of the Airbnb Plus service, wherein the platform inspects properties and provides a badge that presumably signals the quality of the property and the reliability of the host. Our identification strategy relies on the fact that the Airbnb Plus service was launched in different cities at different times, and listings within the cities received the certification at different times. Using a staggered difference-in-differences estimation strategy in conjunction with suitable matching methods, we found that the Airbnb Plus certification increased the weekly booking rate of Plus listings by about 6.8% on average (direct effect). We also found some evidence that non-Plus listings saw a temporary decline in booking rate when one or more nearby properties received a Plus certification (externality effect). The net impact of the Airbnb Plus service on the platform itself was an annual increase in revenue of about $37,500 for the average 2-kilometer zone in a U.S. city that included one or more Plus listings, as compared to matched zones without any Plus listings (local platform effect). We performed additional analyses, including a randomized experiment, to demonstrate the robustness of our findings. Overall, our results suggest that platform-endorsed quality certification has significant economic impacts-not just on the listings that receive the certification but on other listings on the platform as well as on the platform itself. Collapse

Topics: Airbnb website sharing platform peer-to-peer model Google+

Methods: experimental group experiment propensity score method product review robustness check

Review Moderation Transparency and Online Reviews: Evidence from a Natural Experiment

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Jiang, Lianlian (Dorothy); Ravichandran, T.; Kuruzovich, Jason

Abstract: This paper empirically investigates how review moderation transparency affects ... Expand

Abstract: This paper empirically investigates how review moderation transparency affects the volume, length, and negativity of reviews. A change to the Yelp platform in 2010, introducing review moderation and displaying filtered reviews, created a natural experiment. We used a panel dataset of online reviews from the same set of restaurants on both the Yelp and TripAdvisor platforms in a difference-in-differences (DID) model to test how review moderation transparency affected our outcome variables. We found that increasing review moderation transparency negatively affects review volume but positively affects review negativity. The results also indicate that providing review moderation transparency reduces review length, especially for reviews with positive sentiment. Our findings suggest that providing review moderation transparency induces users to invest less effort in review contributions, especially when they are submitting positive reviews. We discuss the theoretical and practical implications of these results as they relate to the design and use of online review platforms. Collapse

Topics: online review user behavior user-generated content digital platform application programming interface

Methods: longitudinal research difference in differences experimental group natural experiment descriptive statistic

How Free Market Entry Affects Creation and Engagement: Evidence from Non-Fungible Tokens

2023 | International Conference on Information Systems | Citations: 0

Authors: Kanellopoulos, Ioannis Filippos; Gutt, Dominik; Tunç, Murat; Li, Ting

Abstract: Content creation costs pose a threat for online marketplaces aiming to attract ... Expand

Abstract: Content creation costs pose a threat for online marketplaces aiming to attract new users. In response, platform managers devise new policies to subsidize these costs for content creators. In this study, we analyze data from a leading NFT marketplace to examine the impact of a lazy minting policy, which enables content creation without upfront fees, on created content, and engagement with that content. On the creation side, we observe a volume-effort trade-off, with creators producing more work for the market but exerting less effort during creation. On the engagement side, we note a decrease in engagement, particularly affecting creators with higher engagement levels prior to the policy change. We explore the mechanism driving this reduction and find that effort and attention play crucial roles, while a larger follower count does not shield creators from decreased engagement. Finally, we discuss our contributions to the literature and its implications for platform managers. Collapse

Topics: information good application programming interface non-fungible token website blockchain

Methods: experimental group longitudinal research regression discontinuity design logarithmic transformation difference in differences

Enhancing Perceived Fairness of AI-Based Personnel Selection Procedures: The Role of AI Certification

2023 | International Conference on Information Systems | Citations: 0

Authors: Kleiner, Romina; Hartwich, Nicole; Antons, David

Abstract: Organizations increasingly integrate artificial intelligence (AI) into their se ... Expand

Abstract: Organizations increasingly integrate artificial intelligence (AI) into their selection procedures, for example, to analyze selection interviews. However, prior research indicates that applicants react negatively to an AI as decision agent in selection interviews. Only few studies have addressed possible mechanisms to mitigate negative effects of AI usage on applicant reactions, calling for increased research attention. The present experimental study (N=180) is among the first to test whether AI certification has the potential to positively influence people's fairness perceptions of AI usage. Consistent with previous research, our results show that people are less attracted to an organization that conducts AI-based (compared to human-based) selection interviews, partially due to lower procedural fairness perceptions. With regards to AI certification, we highlight the crucial role of the certification label's perceived trustworthiness in shaping applicants' procedural fairness perceptions and organizational attraction. Future research should investigate factors that enhance the trustworthiness of an AI certification label. Collapse

Topics: artificial intelligence electronic commerce pandemic data quality anonymity

Methods: qualitative interview experiment mediation analysis statistical hypothesis test experimental design

Theories: signaling theory management theory procedural justice theory

Maximizing Smart Charging of EVs: The Impact of Privacy and Money on Data Sharing

2023 | International Conference on Information Systems | Citations: 0

Authors: Marxen, Hanna; Chemudupaty, Raviteja; Fridgen, Gilbert; Roth, Tamara

Abstract: Smart charging has the potential to shift peak load to times of lower demand, w ... Expand

Abstract: Smart charging has the potential to shift peak load to times of lower demand, which better exploits renewable generation and enhances grid resilience. For increased effectiveness, smart charging requires access to data that consumers might be hesitant to share. To explore which data consumers would share and which factors influence this decision, we adopt the Barth and de Jong's risk-benefit calculation framework to smart charging and conduct an online-survey (n = 479). We find that most respondents who would share charging details with a smart charging application, are ambivalent about location data and would never share calendar details. When presented with concrete monetary rewards, participants lose their initial reservations and would share all data for an amount dependent on the data's sensitivity. Thus, our study contributes to research on the privacy paradox by highlighting the importance of calculations between perceived risks and benefits for the decision to share data. Collapse

Topics: privacy smartphone mobile application geographic information system mobile system

Methods: survey structural equation modeling experimental group SEM tool survey design

Theories: information systems theory

Identifying User Innovations through AI in Online Communities– A Transfer Learning Approach

2023 | International Conference on Information Systems | Citations: 0

Authors: Resch, Christian; Streibel, Julian; Feiter, Tim; Kock, Alexander

Abstract: Identifying innovative users and their ideas is crucial, for example, in crowds ... Expand

Abstract: Identifying innovative users and their ideas is crucial, for example, in crowdsourcing. But, analyzing large amounts of unstructured textual data from such online communities poses a challenge for organizations. Therefore, researchers started developing automated approaches to identify innovative users. Our study introduces an advanced machinelearning approach that minimizes manual work by combining transfer learning with a transformer-based design. We train the model on separate datasets, including an online maker community and various internet texts. The maker community posts represent need-solution pairs, which express needs and describe fitting prototypes. Then, we transfer the model and identify potential user innovations in a kitesurfing community. We validate the identified posts by manually checking a subsample and analyzing how words affect the model's classification decision. This study contributes to the growing portfolio of user innovation identification by combining state-of-the-art natural language processing and transfer learning to improve automated identification. Collapse

Topics: innovation management online community internet technology computer hardware open source

Methods: machine learning BERT qualitative coding transformer model natural language processing

Know Thy Context: Parsing Contextual Information from User Reviews for Recommendation Purposes

2022 | Information Systems Research | Citations: 1

Authors: Bauman, Konstantin; Tuzhilin, Alexander

Abstract: In this paper, we study an important problem of parsing contextual information f ... Expand

Abstract: In this paper, we study an important problem of parsing contextual information from user reviews for recommendation purposes. First, we study the ways contextual information is expressed in user reviews and obtain novel insights about it. Among other things, we demonstrate that such type of information tends to appear at the beginning of the review, in longer sentences, in the sentences written in the past tense or using gerund form, and in the sentences referring to some points in time. Second, we propose a novel context parsing method for systematically extracting contextual information from user-generated reviews that relies on the insights obtained in our study. We apply the proposed method to three different Yelp applications (restaurants, hotels, and beauty & spas) and demonstrate that it works well and leads to better recommendation performance than the baseline approaches. Our method systematically extracts more comprehensive sets of relevant contextual variables and corresponding phrases than the baselines. Our analysis also shows the importance of the newly discovered contextual information for recommendation purposes. The obtained results and the proposed method can help to get more comprehensive knowledge about contextual variables in a given application that leads to better recommendations. Collapse

Topics: online review recommender system logistics management user experience user-generated content

Methods: word2vec hierarchical clustering machine learning product review experiment

Social media crowdsourcing for rapid damage assessment following a sudden-onset natural hazard event

2021 | International Journal of Information Management | Citations: 0

Authors: Li, Lingyao; Bensi, Michelle; Cui, Qingbin; Baecher, Gregory B.; Huang, You

Abstract: Rapid appraisal of damages related to hazard events is of importance to first re ... Expand

Abstract: Rapid appraisal of damages related to hazard events is of importance to first responders, government agencies, insurance industries, and other private and public organizations. While satellite monitoring, ground-based sensor systems, inspections and other technologies provide data to inform post-disaster response, crowdsourcing through social media is an additional and novel data source. In this study, the use of social media data, prin­ cipally Twitter postings, is investigated to make approximate but rapid early assessments of damages following a disaster. The goal is to explore the potential utility of using social media data for rapid damage assessment after sudden-onset hazard events and to identify insights related to potential challenges. This study defines a textbased damage assessment scale for earthquake damages, and then develops a text classification model for rapid damage assessment. Although the accuracy remains a challenge compared to ground-based instrumental readings and inspections, the proposed damage assessment model features rapidity with large amounts of data at spatial densities that exceed those of conventional sensor networks. The 2019 Ridgecrest, California earthquake sequence is investigated as a case study. Collapse

Topics: Twitter earthquake social media natural hazard Wikipedia

Methods: term frequency–inverse document frequency word embedding descriptive statistic statistical hypothesis test deep learning

Creativity Loading – Please Wait! Investigating the Relationship between Interruption, Mind Wandering and Creativity

2020 | HICSS | Citations: 0

Authors: Baumgart, Thorben Lukas; Oschinsky, Frederike Marie; Klesel, Michael; Niehaves, Bjoern

Abstract: With the advancement of information technologies, routine tasks are increasingly ... Expand

Abstract: With the advancement of information technologies, routine tasks are increasingly supported by information systems, which is why ideation and creativity is becoming more and more important. We know from many anecdotes that creative ideas emerge when our mind is wandering instead of being focused on the task at hand. Yet, most information systems that are used for work-related purposes offer only little opportunities for task-unrelated thoughts. In contrast, current literature shows that most information technology is designed to keep our attention. In order to better understand the value of mind wandering, we propose an experimental design that incorporates interruptions that vary in their length with the objective to stimulate episodes of mind wandering and thus positively impact creativity. We provide initial insights on how the experiment should designed and discuss implications for future research. Collapse

Topics: knowledge work usability systems design task productivity armed conflict

Methods: experiment regression analysis method survey self reported survey laboratory experiment