Rumor Classification through a Multimodal Fusion Framework and Ensemble Learning

2023 | Information Systems Frontiers | Citations: 0

Authors: Azri, Abderrazek; Favre, Cécile; Harbi, Nouria; Darmont, Jérôme; Noûs, Camille

Abstract: The proliferation of rumors on social media has become a major concern due to it ... Expand

Abstract: The proliferation of rumors on social media has become a major concern due to its ability to create a devastating impact. Manually assessing the veracity of social media messages is a very time-consuming task that can be much helped by machine learning. Most message veracity verification methods only exploit textual contents and metadata. Very few take both textual and visual contents, and more particularly images, into account. Moreover, prior works have used many classical machine learning models to detect rumors. However, although recent studies have proven the effectiveness of ensemble machine learning approaches, such models have seldom been applied. Thus, in this paper, we propose a set of advanced image features that are inspired from the field of image quality assessment, and introduce the Multimodal fusiON framework to assess message veracIty in social neTwORks (MONITOR), which exploits all message features by exploring various machine learning models. Moreover, we demonstrate the effectiveness of ensemble learning algorithms for rumor detection by using five metalearning models. Eventually, we conduct extensive experiments on two real-world datasets. Results show that MONITOR outperforms state-of-the-art machine learning baselines and that ensemble models significantly increase MONITOR’s performance. Collapse

Topics: Twitter social network Python microblog logistics management

Methods: computational algorithm machine learning experiment meta learning ensemble learning

Single-Sourcing vs. Multisourcing: An Empirical Analysis of Large Information Technology Outsourcing Arrangements

2023 | Information Systems Research | Citations: 0

Authors: Bapna, Ravi; Gupta, Alok; Ray, Gautam; Singh, Shweta

Abstract: As the information technology (IT) services landscape matures, clients are incre ... Expand

Abstract: As the information technology (IT) services landscape matures, clients are increasingly adopting multisourcing arrangements that involve multiple vendors. Although a large body of information systems (IS) literature addresses issues of whether to outsource (to a single vendor), what types of contracts to use, and how to achieve optimal relational governance, little is known about the antecedents and consequents of the single versus multisourcing decision. Moreover, while conceptual and analytical models of single-sourcing versus multisourcing have been developed, there is no empirical IS research using a large-scale data set with rigorous econometric analysis that examines the antecedents and consequents of multisourcing in the IT context. This paper fills this void, using the transaction cost economic lens and a data set of 49,057 large IT outsourcing arrangements that spans multiple industries and dates back 25 years. We find that there is a curvilinear relationship between number of IT services in an IT outsourcing arrangement and the likelihood of multisourcing. This relationship increases as the number of IT services increases to up to five services and then decreases. For managers who plan to multisource IT outsourcing arrangements, this research provides guidance to minimize exchange hazards through a better understanding of the relationship between sourcing choice, client IT outsourcing capabilities, the competitiveness of the vendor landscape, and the number of IT services in an IT outsourcing arrangement. We provide empirical evidence that the choice between single-sourcing and multisourcing is material to the performance of outsourcing contracts as an incorrect sourcing choice is likely to result in negative contract outcomes. History: Paul A. Pavlou, Senior Editor; Ning Su, Associate Editor. Collapse

Topics: outsourcing system integration IS management service desk data center

Methods: XGBoost robustness check machine learning k-nearest neighbor statistical hypothesis test

Theories: transaction cost economics game theory

Text Analytics

2023 | HICSS | Citations: 0

Authors: Cogburn, D.; Hine, M.; Yoon, V.

Abstract: This virtual minitrack for HICSS-56 recognizes that most global collaboration s ... Expand

Abstract: This virtual minitrack for HICSS-56 recognizes that most global collaboration systems, social media, and information systems of all types, generate enormous amounts of textual data, including system logs, email archives, websites, blog posts, meeting transcripts, speeches, annual reports, published material, and social media posts.While this structured, semistructured, and unstructured textual data is readily available, it presents tremendous challenges to researchers trying to analyze these large bodies of text with traditional methods. Text mining in big data analytics is an increasingly important technique for an interdisciplinary group of scholars, practitioners, government officials, and international organizations. This minitrack explores the tools, techniques, and insights generated from the analysis of text data. Collapse

Topics: application programming interface

Methods: natural language processing RoBERTa experiment question answering classification method

Incorporating Multiple Knowledge Sources for Targeted Aspect-based Financial Sentiment Analysis

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

Authors: Du, Kelvin; Xing, Frank; Cambria, Erik

Abstract: Combining symbolic and subsymbolic methods has become a promising strategy as re ... Expand

Abstract: Combining symbolic and subsymbolic methods has become a promising strategy as research tasks in AI grow increasingly complicated and require higher levels of understanding. Targeted Aspect-based Financial Sentiment Analysis (TABFSA) is an example of such complicated tasks, as it involves processes like information extraction, information specification, and domain adaptation. However, little is known about the design principles of such hybrid models leveraging external lexical knowledge. To fill this gap, we define anterior, parallel, and posterior knowledge integration and propose incorporating multiple lexical knowledge sources strategically into the fine-tuning process of pre-trained transformer models for TABFSA. Experiments on the Financial Opinion mining and Question Answering challenge (FiQA) Task 1 and SemEval 2017 Task 5 datasets show that the knowledge-enabled models systematically improve upon their plain deep learning counterparts, and some outperform state-of-the-art results reported in terms of aspect sentiment analysis error. We discover that parallel knowledge integration is the most effective and domain-specific lexical knowledge is more important according to our ablation analysis. Collapse

Topics: microblog domain-specific language Twitter social media knowledge graph

Methods: sentiment analysis RoBERTa transformer model BERT XLNet

Emotional Synchrony and Viewers’ Consumption: Evidence from Live Streaming of Virtual Idols

2023 | International Conference on Information Systems | Citations: 0

Authors: Duan, Menghan; Zhang, Yueyue; Zhang, Qi; Zhang, Cheng

Abstract: Live streaming has become increasingly popular in recent years for users to bro ... Expand

Abstract: Live streaming has become increasingly popular in recent years for users to broadcast live events or experiences to an online audience in real-time. With the prevalence of the metaverse, virtual idols appear on the stage of live streaming. Unlike real human streamers, virtual idols are computer-generated avatars whose appearance does not exist in the physical world. Though existing literature has documented the effect of emotional displays of human streamers on viewers' behavior, whether emotional displays of avatar streamers affect viewers' behavior, especially viewers' consumption behavior has not yet been explored. To fill this gap, we focus on the live streaming of virtual idols and conduct deep learning approaches to investigate the emotional synchrony between avatar streamers and their viewers based on moment-tomoment data. Our analysis of large-scale video data shows that the larger the discrepancy between the streamers' acoustic-and text-emotions, the more likely the viewers will pay. This study sheds light on how avatars can be designed to leverage emotion to engage viewers in more consumption. Collapse

Topics: marketing management human AI collaboration microblog open source Python

Methods: deep learning computational algorithm XGBoost machine learning gradient boosting

Fraud Detection in Mobile Payment Systems using an XGBoost-based Framework

2023 | Information Systems Frontiers | Citations: 0

Authors: Hajek, Petr; Abedin, Mohammad Zoynul; Sivarajah, Uthayasankar

Abstract: Mobile payment systems are becoming more popular due to the increase in the numb ... Expand

Abstract: Mobile payment systems are becoming more popular due to the increase in the number of smartphones, which, in turn, attracts the interest of fraudsters. Extant research has therefore developed various fraud detection methods using supervised machine learning. However, sufficient labeled data are rarely available and their detection performance is negatively affected by the extreme class imbalance in financial fraud data. The purpose of this study is to propose an XGBoost-based fraud detection framework while considering the financial consequences of fraud detection systems. The framework was empirically validated on a large dataset of more than 6 million mobile transactions. To demonstrate the effectiveness of the proposed framework, we conducted a comparative evaluation of existing machine learning methods designed for modeling imbalanced data and outlier detection. The results suggest that in terms of standard classification measures, the proposed semi-supervised ensemble model integrating multiple unsupervised outlier detection algorithms and an XGBoost classifier achieves the best results, while the highest cost savings can be achieved by combining random under-sampling and XGBoost methods. This study has therefore financial implications for organizations to make appropriate decisions regarding the implementation of effective fraud detection systems. Collapse

Topics: fraud detection mobile system mobile payment electronic payment Python

Methods: XGBoost machine learning anomaly detection supervised learning experiment

Resource Allocation for Heterogeneous Computing Tasks in Wirelessly Powered MEC-enabled IIOT Systems

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

Authors: Hu, Yixiang; Deng, Xiaoheng; Zhu, Congxu; Chen, Xuechen; Chi, Laixin

Abstract: Integrating wireless power transfer with mobile edge computing (MEC) has become ... Expand

Abstract: Integrating wireless power transfer with mobile edge computing (MEC) has become a powerful solution for increasingly complicated and dynamic industrial Internet of Things (IIOT) systems. However, the traditional approaches overlooked the heterogeneity of the tasks and the dynamic arrival of energy in wirelessly powered MEC-enabled IIOT systems. In this article, we formulate the problem of maximizing the product of the computing rate and the task execution success rate for heterogeneous tasks. To manage energy harvesting adaptively and select appropriate computing modes, we devise an online resource allocation and computation offloading approach based on deep reinforcement learning. We decompose this approach into two stages: an offloading decision stage and a stopping decision stage. The purpose of the offloading decision stage is to select the computing mode and dynamically allocate the computation round length for each task after learning from the channel state information and the task experience. This stage allows the system to support heterogeneous computing tasks. Subsequently, in the second stage, we adaptively adjust the number of fading slots devoted to energy harvesting in each round in accordance with the status of each fading slot. Simulation results show that our proposed algorithm can better allocate resources for heterogeneous tasks and reduce the ratio of failed tasks and energy consumption when compared with several existing algorithms. Collapse

Topics: resource allocation edge computing decision quality

Methods: computational algorithm reinforcement learning simulation experiment PyTorch

Diffusion of real versus misinformation during a crisis event: A big data-driven approach

2023 | International Journal of Information Management | Citations: 0

Authors: King, Kelvin K.; Wang, Bin

Abstract: Misinformation has captured the interest of academia in recent years with severa ... Expand

Abstract: Misinformation has captured the interest of academia in recent years with several studies looking at the topic broadly with inconsistent results. In this research, we attempt to bridge the gap in the literature by examining the impacts of user-, time-, and content-based characteristics that affect the virality of real versus misinformation during a crisis event. Using a big data-driven approach, we collected over 42 million tweets during Hurricane Harvey and obtained 3589 original verified real or false tweets by cross-checking with fact-checking websites and a relevant federal agency. Our results show that virality is higher for misinformation, novel tweets, and tweets with negative sentiment or lower lexical density. In addition, we reveal the opposite impacts of sentiment on the virality of real news versus misinformation. We also find that tweets on the environment are less likely to go viral than the baseline religious news, while real social news tweets are more likely to go viral than misin­ formation on social news. Collapse

Topics: Twitter misinformation social media hurricane big data

Methods: machine learning computational algorithm natural language processing decision tree classification gradient boosting

Using AI to Improve Sustainable Agricultural Practices: A Literature Review and Research Agenda

2023 | Communications of the Association for Information Systems | Citations: 0

Authors: Lakshmi, Vijaya; Corbett, Jacqueline

Abstract: The world is confronted with the grand challenge of food insecurity amidst grow ... Expand

Abstract: The world is confronted with the grand challenge of food insecurity amidst growing populations and the climate crisis. Artificial intelligence (AI) deployed in agricultural decision support systems (AgriDSS) raises both hopes and concerns for increasing agricultural productivity in sustainable ways. We conduct a scoping review to uncover the roadblocks to the use of AI-supported AgriDSS in sustainable agriculture. Based on the corpus of 121 articles, we find that the effective use of AI-supported AgriDSS is hindered at technical, social, ethical, and ecological levels. Then, drawing on the experiential learning perspective, we propose how conjoint experiential learning (CEL) can enhance sustainable agricultural practices by enhancing both AI and human learning and overcoming roadblocks in using AgriDSS. Based on this conceptual framework, we build a research agenda that suggests blind spots and possible directions for future research. Collapse

Topics: artificial intelligence decision support system human computer interaction human in the loop decision making

Methods: literature sample literature study computational algorithm qualitative coding artificial neural network

Estimating Life Cycle Sales of Technology Products with Frequent Repeat Purchases: A Fractional Calculus-Based Approach

2023 | Information Systems Research | Citations: 0

Authors: Lotfi, Aslan; Jiang, Zhengrui; Lotfi, Ali; Jain, Dipak C.

Abstract: Accurately predicting the sales trajectory of a product in its life cycle is cri ... Expand

Abstract: Accurately predicting the sales trajectory of a product in its life cycle is critically important for firms’ medium- and long-term planning. Because classic product-diffusion models such as the Bass model consider only initial product purchases, they are ill-fitted for sales prediction for today’s technology products with a shorter life cycle and frequent repeat purchases or subscription renewals. Despite the long tradition of product diffusion research, there exists no viable model option when repeat purchases constitute a large proportion of product sales. The present study introduces a new sales growth model, termed the generalized diffusion model with repeat purchases (GDMR), to fill this void. The GDMR formulates the growth rate of sales using a noninteger-order integral equation rather than the integer-order differential equation typically adopted in existing diffusion models. The GDMR is parsimonious and easy to implement. Empirical results show that the GDMR fits sales data with varying proportions of repeat purchases quite well, making it suitable for predicting sales of a wide variety of products. In addition, the GDMR can be extended to incorporate marketing mix variables, thus enhancing its applicability in business decision making. Furthermore, using both real and simulated data, we show that the GDMR can reliably recover a product’s adoption trend using only sales data, thus cementing its theoretical validity and empirical effectiveness. Finally, we show that the GDMR is superior to generic time series and machine learning models in predicting future product sales. History: Ram Gopal, Senior Editor; Wenjing Duan, Associate Editor. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.1131. Collapse

Topics: marketing management DVD innovation management diffusion of innovation tablet

Methods: longitudinal research time series analysis machine learning simulation autoregressive integrated moving average