The Sound of Progress: Investigating the Representation of Artificial Intelligence in Music

2023 | International Conference on Business Informatics | Citations: 0

Authors: Banh, Leonardo; Strobel, Gero

Abstract: The role of artificial intelligence in daily life is constantly advancing and h ... Expand

Abstract: The role of artificial intelligence in daily life is constantly advancing and has become an important topic of discussion. With music and its lyrics being a vehicle to express topics of society, this paper investigates how artificial intelligence is perceived by musicians and reflected in their songs. By analyzing the lyrics of over 1,200 songs over three decades, this work applies sentiment analysis to extract polarities and emotions. The results provide insights into how musicians view and reflect the impact of artificial intelligence on society and how this is reflected in their song texts. The findings show an increase in songs mentioning artificial intelligence-related terms, with a trend of more songs implying negativity, such as anger. However, minor increases in positive emotions indicate musicians' ambivalent views on hopes and fear of artificial intelligence. Collapse

Topics: artificial intelligence deepfake database system

Methods: sentiment analysis deep learning machine learning language model simple linear regression

Theories: communication theory

Modern Centaurs: How Humans and AI Systems Interact in Sales Forecasting

2023 | European Conference On Information Systems | Citations: 0

Authors: Beese, Jannis; Fahse, Tobias

Abstract: Recent achievements of artificial intelligence (AI) have caused organizations t ... Expand

Abstract: Recent achievements of artificial intelligence (AI) have caused organizations to increasingly bring AI capabilities into their core business processes. Such AI-supported business processes often result in human-AI hybrid systems, which consist of an AI system, which performs most of the execution, and humans, who monitor this execution and occasionally provide additional inputs and overrides. Using sales data from Walmart, we conduct an online study to investigate if human supervision can improve upon state-of-the-art AI forecasts. Furthermore, we analyze the perceptions and behavioral intentions of the human participants over time. We find that human interventions consistently lead to less accurate forecasts and that participants initially underestimate the AI system's accuracy and overestimate their own potential to improve upon AI forecasts. However, perceptions quickly shift over the course of the study, causing the participants to perceive the AI system increasingly favorably, which also leads to behavioral changes and better hybrid system performance. Collapse

Topics: artificial intelligence IT productivity information system use task productivity perceived usefulness

Methods: regression analysis method survey LightGBM conceptual modelling experiment

Theories: technology acceptance model

SOLVING THE DATA-DRIVEN NEWSVENDOR WITH ATTENTION TO TIME

2023 | European Conference On Information Systems | Citations: 0

Authors: Feddersen, Leif; Cleophas, Catherine

Abstract: Inventory management systems support firms in planning for an uncertain future ... Expand

Abstract: Inventory management systems support firms in planning for an uncertain future by using demand forecasts and optimization models to make restocking decisions. Recent work on the "data-driven" newsvendor found that incorporating machine learning (ML) can improve the success of inventory management by accounting for demand-driving information. However, ML methods are infamously hard to interpret, which may hinder their acceptance. To ameliorate this, we show how to apply an interpretable attention-based architecture, the Temporal Fusion Transformer (TFT), to the data-driven newsvendor problem. Our approach replicates and extends the original TFT time series forecasting method to the inventory management domain. We evaluate our method on two real-world retail datasets, each covering 260 perishable food items, and provide domain-specific benchmarks. The computational study illustrates TFT's interpretable predictions and their comparatively high accuracy. Our work aims to lay the groundwork for further design science research on transparency in human-AI collaboration in this domain. Collapse

Topics: human AI collaboration human computer interaction Python decision making accounting

Methods: time series analysis longitudinal research artificial neural network feature engineering machine learning

Theories: learning theory

MDSCAN: AN EXPLAINABLE ARTIFICIAL INTELLIGENCE ARTIFACT FOR MENTAL HEALTH SCREENING

2023 | European Conference On Information Systems | Citations: 0

Authors: Tutun, Salih; Bhattacherjee, Anol; Topuz, Kazim; Tosyali, Ali; Li, Gorden

Abstract: This paper presents a novel artifact called MDscan that can help mental health ... Expand

Abstract: This paper presents a novel artifact called MDscan that can help mental health professionals quickly screen a large number of patients for ten mental disorders. MDscan uses patient responses to the SCL-90-R clinical questionnaire to create a full-color image, similar to radiological images, which identifies which disorder or combination of disorders may afflict a patient, the severity of the disorder, and the underlying logic of this prediction, using an explainable artificial intelligence (XAI) approach. While prior artificial intelligence (AI) tools have seen limited acceptance in clinical practice because of the lack of transparency and interpretability in their "black box" models, the XAI approach used in MDscan is a "white box" model that elaborates which patient feature contributes to the predicted outcome and to what extent. Using patient data from a mental health clinic, we demonstrate that MDscan outperforms current (expert-based) clinical practice by an average of 20%. Collapse

Topics: explainable artificial intelligence shapley additive explanation local interpretable model agnostic explanation IT security artificial intelligence

Methods: computational algorithm machine learning data transformation t-distributed stochastic neighbor embedding survey

Unlocking the Power of Voice for Financial Risk Prediction: A Theory-Driven Deep Learning Design Approach

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Yang, Yi; Qin, Yu; Fan, Yangyang; Zhang, Zhongju

Abstract: Unstructured multimedia data (text and audio) provides unprecedented opportunit ... Expand

Abstract: Unstructured multimedia data (text and audio) provides unprecedented opportunities to derive actionable decision-making in the financial industry, in areas such as portfolio and risk management. However, due to formidable methodological challenges, the promise of business value from unstructured multimedia data has not materialized. In this study, we use a design science approach to develop DeepVoice, a novel nonverbal predictive analysis system for financial risk prediction, in the setting of quarterly earnings conference calls. DeepVoice forecasts financial risk by leveraging not only what managers say (verbal linguistic cues) but also how managers say it (vocal cues) during the earnings conference calls. The design of DeepVoice addresses several challenges associated with the analysis of nonverbal communication. We also propose a two-stage deep learning model to effectively integrate managers' sequential vocal and verbal cues. Using a unique dataset of 6,047 earnings call samples (audio recordings and textual transcripts) of S&P 500 firms across four years, we show that DeepVoice yields remarkably lower risk forecast errors than that achieved by previous efforts. The improvement can also translate into nontrivial economic gains in options trading. The theoretical and practical implications of analyzing vocal cues are discussed.Challenge 1: Time variation. Managers' vocal features can vary substantially during conference calls. For example, during the presentation section, when the manager is reading a forward-looking statement, the voice pitch may be quite stable. However, individuals' vocal cues may change as a result of being nervous, uncertain, or excited (Scherer et al., 1991). As such, in the question-answer section, when the manager is being scrutinized by analysts, the voice pitch may change. Mayew et al. (2020) found that the voice pitch of managers during dialogues with analysts is lower by about 4 Hz, on average, compared to their voice pitch during presentation sessions. Therefore, the time-varying patterns of managers' vocal cues may contain useful information. However, prior studies have ignored the time-varying pattern of managers' vocal cues in earnings conference calls (Mayew et al., 2020;, and it is unclear how a predictive model could effectively summarize time-varying vocal sequences.Challenge 2: Vocal-verbal integration. According to nonverbal communication theory (Mehrabian, 1972), vocal cues play a key role in nonverbal communication, as they can either affirm or discredit a message. For example, if a manager claims the company has strong future growth but uses a pessimistic tone of voice, market participants listening to the conference call may spot the irregularity and interpret the verbal message differently. This implies that to accurately gauge the information contained in managers' communication, one should integrate verbal language with the accompanying vocal cues. However, existing computational models (Poria et al., 2017) are limited in terms of integrating these two different communication channels (i.e., vocal and verbal).Challenge 3: Vocal complexity. Identifying the specific acoustic constructs from voice is a complex process, and the literature is still evolving without any consensus on an appropriate model for measuring affective states, emotions, and trust (Mayew & Venkatachalam, 2013). There is also little agreement about how a speaker's vocal cues should be combined to identify emotional states (Schuller, 2010)-e.g., which vocal cues to investigate and measure and how much weight to place on each vocal cue. As a result, attempts to develop constructs from vocal cues may suffer from high measurement errors. Collapse

Topics: database system enterprise information system website accounting social media

Methods: deep learning experiment meta design machine learning design artifact

Theories: transaction cost economics communication theory

Moral Hazard and Transparency in Peer-to-Peer Auto Insurance with Telematics

2023 | International Conference on Information Systems | Citations: 0

Authors: Zhang, Yuxin; du, yalei; Zhang, Yuanyuan; Zhang, Quan

Abstract: Peer -to-peer (P2P) insurance uses new technology to connect policyholders and ... Expand

Abstract: Peer -to-peer (P2P) insurance uses new technology to connect policyholders and brings about disruptive innovation. While P2P insurance serving people with relatively high degrees of social connection, like friends and relatives, has been theoretically and practically underpinned, there is a lack of understanding about its viability or efficiency in serving strangers with few to no social ties as moral hazard may be substantial. In this paper, we bridge the gap by empirically measuring moral hazard in a P2P auto insurance where the insured individuals are strangers. Our research findings remove an obstacle that may hinder a broad application of the P2P insurance model among large groups of individuals. Moreover, we investigate factors that mitigate moral hazard and study the impact of transparency in premium balance on driving safety. We show that the transparency allows people to learn vicariously from peers' lessons and lets them drive more safely. Collapse

Topics: peer-to-peer model moral hazard price management business model mobile application

Methods: experimental group longitudinal research difference in differences causality analysis propensity score method

A machine learning investigation of factors that contribute to predicting cognitive performance: Difficulty level, reaction time and eye-movements

2022 | Decision Support Systems | Citations: 0

Authors: Bachurina, Valentina; Sushchinskaya, Svetlana; Sharaev, Maxim; Burnaev, Evgeny; Arsalidou, Marie

Abstract: Predicting accuracy in cognitively challenging tasks has potential applications ... Expand

Abstract: Predicting accuracy in cognitively challenging tasks has potential applications in education and industry. Task demand has been linked with increases in response time and variations in reaction time and eye-tracking metrics, however, machine learning research has not been used to predict performance on tasks with multiple levels of difficulty. We report data on adult participants who performed tasks of mental attentional capacity with six levels of difficulty and use machine learning methods to predict accuracy scores considering metrics associated with task difficulty, reaction time and eye movements. Results show that machine learning models can robustly predict performance with reaction times and difficulty level being the strongest predictors. Eye-tracking indices can also predict accuracy independently, with the most important features of the model driven by the number of fixations, number of saccades, duration of the current fixation and pupil size. Practical and theoretical impli­ cations of the results are discussed. Collapse

Topics: Python decision support system software developer

Methods: oculometry machine learning descriptive statistic computational algorithm regression analysis method

Theories: cognitive theory

Designing Flipped Learning Activities for Beginner Programming Course

2022 | Americas Conference on Information Systems | Citations: 0

Authors: Gan, Benjamin Kok Siew; Ouh, Eng Lieh

Abstract: This study focuses on designing flipped classroom learning activities across pr ... Expand

Abstract: This study focuses on designing flipped classroom learning activities across pre-class problem-based exercises; with in-class active discussions and practical problem-solving sessions; and follow up with postclass problem-based labs and assessments. We evaluate the effectiveness of our learning activities based on student surveys, course feedback, grades, and teacher feedback for a beginner programming course with non-IS students. We describe detail programming learning activities with comparisons to existing practices based on related work. Our findings are that majority of students (86%) agreed with flipped classroom, but teachers should be aware of the 14% who disagreed and cater for them. Teachers should avoid overwhelming students with extra exercises (making it optional) but may challenge students who want them and have confidence. With data provided, we hope teachers can make a better-informed decision when choosing flipped classroom, problem-based learning activities for beginner programming course. KeywordsLearning activities, flipped classroom, problem-based learning, beginner programming course. Collapse

Topics: Python problem solving bring your own device laptop computer gamification

Methods: parametric test Student's t-test survey nonparametric test literature study

Algorithmically Controlled Automated Decision-Making and Societal Acceptability: Does Algorithm Type Matter?

2022 | HICSS | Citations: 0

Authors: Grange, Camille

Abstract: As technological capabilities expand, an increasing number of decision-making pr ... Expand

Abstract: As technological capabilities expand, an increasing number of decision-making processes (e.g., rankings, selections, exclusions) are being delegated to computerized systems. In this paper, we examine the societal acceptability of a consequential decisionmaking system (university admission) to those subject to the decision (i.e., applicants). We analyze two key drivers: the nature of the decision-making agent (a human vs an algorithm) and the decision-making logic used by the agents (predetermined vs emerging). Consistent with uniqueness neglect theory, we propose that applicants will be more positive toward the use of human agents compared to computerized systems. Consistent with the theory of procedural justice, we further argue that applicants will find the use of a predetermined logic to be more acceptable than an emerging logic. We present the details and results of a factorial survey designed to test our theoretical model. Collapse

Topics: decision making artificial intelligence algorithmic transparency electronic market

Methods: computational algorithm machine learning survey statistical hypothesis test factorial experiment

Theories: procedural justice theory

Continued usage of smart wearable devices (SWDs): cross-level analysis of gamification and network externality

2022 | Electronic Markets | Citations: 0

Authors: Tsai, Juin-Ming; Hung, Shiu-Wan; Lin, Guan-Ting

Abstract: With the increasing maturity of mobile networks and big data technology, smart w ... Expand

Abstract: With the increasing maturity of mobile networks and big data technology, smart wearable devices (SWDs) are regarded as a new technology trend following smartphones. Especially during the COVID-19 pandemic, the increase in telework and the growing interest in self-health monitoring have greatly promoted the market growth of SWDs. This study aimed to investigate the factors affecting the continued use of SWDs. A cross-level analysis model that integrates technical characteristics, gamification theory, perceived value theory, and network externality was constructed. A hierarchical linear model was employed to evaluate the data and test it against the hypotheses. The empirical results showed that, at the individual level, gamification enhances users’ value perceptions. Users pay more attention to rewards in gamification than to competition. Rewards were also found to effectively promote the users’ value perception and increase the intention to continue using the device. At the group level, the effect of network externality significantly influences the intention to continue using SWDs. Moreover, SWDs are associated with the phenomenon by which consumers conspicuously display and highlight their own characteristics, and this attribute is also a crucial factor enticing consumers to continue using SWDs. Developers should therefore establish clear product positioning and strengthen interactivity as early as possible to build a loyal customer base. Collapse

Topics: gamification mobile system smart bracelet smart watch network effect

Methods: survey hierarchical linear modeling descriptive statistic statistical hypothesis test literature study