What Can Online Doctor Reviews Tell Us? A Deep Learning Assisted Study of Telehealth Service

2023 | HICSS | Citations: 0

Authors: Hao, H.; Zhang, B.; Zhan, Y.; Wu, J.

Abstract: The present study develops a novel deep learning method which assists text mini ... Expand

Abstract: The present study develops a novel deep learning method which assists text mining of online doctor reviews to extract underlying sentiment scores. Those scores can be used to estimate a healthcare service quality model to investigate how the online doctor reviews impact the online doctor consultation demand. Based on the data from the largest online health platforms in China, our model results show that the underlying sentiment scores have statistically significant impacts on the demand of online doctor consultation. Theoretically, the present study constructs an innovative deep learning algorithm with a better performance than four widely used text mining methods, which can be applied to text mining of many online forums or social media texts. Empirically, our model results show what factors impact the health service quality and online doctor consultation demand, and following those factors, healthcare professionals can improve their service. Collapse

Topics: service quality online review social media Python user-generated content

Methods: sentiment analysis natural language processing deep learning experimental group doc2vec

A decision support framework to incorporate textual data for early student dropout prediction in higher education

2023 | Decision Support Systems | Citations: 0

Authors: Phan, Minh; De Caigny, Arno; Coussement, Kristof

Abstract: Managing student dropout in higher education is critical, considering its substa ... Expand

Abstract: Managing student dropout in higher education is critical, considering its substantial impacts on students’ lives, academic institutions, and society as a whole. Using predictive modeling can be instrumental for this task, as a means to identify dropouts proactively on the basis of student characteristics and their academic performance. To enhance these predictions, textual student feedback also might be relevant; this article proposes a hybrid decision support framework that combines predictive modeling with student segmentation efforts. A real-life data set from a French higher education institution, containing information of 14,391 students and 62,545 feedback documents, confirms the superior performance of the proposed framework, in terms of the area under the curve and top decile lift, compared with various benchmarks. In contributing to decision support system research, this study (1) proposes a new framework for automatic, data-driven segmentation of students based on textual data; (2) compares multiple text representation methods and confirms that incorporating student textual feedback data improves the predictive performance of student dropout models; and (3) establishes useful insights to help decision-makers anticipate and manage student dropout behaviors. Collapse

Topics: decision support decision support system electronic mail

Methods: machine learning doc2vec data transformation BERT computational algorithm

A Modular Social Sensing System for Personalized Orienteering in the COVID-19 Era

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

Authors: Pilato, Giovanni; Persia, Fabio; Ge, Mouzhi; Chondrogiannis, Theodoros; D’Auria, Daniela

Abstract: Orienteering or itinerary planning algorithms in tourism are used to optimize tr ... Expand

Abstract: Orienteering or itinerary planning algorithms in tourism are used to optimize travel routes by considering user preference and other constraints, such as time budget or traffic conditions. For these algorithms, it is essential to explore the user preference to predict potential points of interest (POIs) or tourist routes. However, nowadays, user preference has been significantly affected by COVID-19, since health concern plays a key tradeoff role. For example, people may try to avoid crowdedness, even if there is a strong desire for social interaction. Thus, the orienteering or itinerary planning algorithms should optimize routes beyond user preference. Therefore, this article proposes a social sensing system that considers the tradeoff between user preference and various factors, such as crowdedness, personality, knowledge of COVID-19, POI features, and desire for socialization. The experiments are conducted on profiling user interests with a properly trained fastText neural network and a set of specialized Naïve Bayesian Classifiers based on the “Yelp!” dataset. Also, we demonstrate how to approach and integrate COVID-related factors via conversational agents. Furthermore, the proposed system is in a modular design and evaluated in a user study; thus, it can be efficiently adapted to different algorithms for COVID-19-aware itinerary planning. Collapse

Topics: user satisfaction social network personality conversational agent Twitter

Methods: computational algorithm fastText machine learning experiment descriptive statistic

Empowering Recommender Systems in ITSM: A Pipeline Reference Model for AI-Based Textual Data Quality Enrichment

2023 | DESRIST | Citations: 0

Authors: Reinhard, Philipp; Li, Mahei Manhai; Dickhaut, Ernestine; Peters, Christoph; Leimeister, Jan Marco

Abstract: AI-based recommendation systems to augment working conditions in the field of IT ... Expand

Abstract: AI-based recommendation systems to augment working conditions in the field of IT service management (ITSM) have attracted new attention. However, many IT support organizations possess high volumes of tickets but are confronted with low quality, to which they train the underlying models of their AI systems. In particular, support tickets are documented insufficiently due to time pressure and lack of motivation. Following design science research, we design and evaluate an analytics pipeline to address the data quality issue. The pipeline can be applied to assess and extract high-quality support tickets for subsequent model training and operation. Based on a data set of 60.000 real-life support tickets from a manufacturing company, we develop the artifact, instantiate a recommender system and achieve a higher prediction performance in comparison to naïve enrichment methods. In terms of data management literature, we contribute to the understanding of assessing textual ticket data quality. By deriving a pipeline reference model, we move towards a general approach to designing machine learning-driven data quality analytics pipelines for attached recommender systems. Collapse

Topics: data quality recommender system system support shapley additive explanation database system

Methods: machine learning reference modelling design artifact cluster analysis topic model

When machines trade on corporate disclosures: Using text analytics for investment strategies

2023 | Decision Support Systems | Citations: 0

Authors: Schmitz, Hans Christian; Lutz, Bernhard; Wolff, Dominik; Neumann, Dirk

Abstract: Can you make profits by trading on corporate disclosures using machine learning? ... Expand

Abstract: Can you make profits by trading on corporate disclosures using machine learning? In this study, we aim to obtain a conservative estimate of profitability, while accounting for the combination of several important realworld aspects. Specifically, we consider the holistic research problem that combines model predictions based on the textual content of corporate disclosures and trading strategies while accounting for transaction costs, order clearance periods, post-publication returns, and liquidity filtering. Furthermore, we aim to understand how the resulting profits are influenced by different model and trading strategy parameters. Based on 354,992 form 8-K filings and 10,204 ad hoc announcements, we find that the proposed trading strategies yield up to 7.81 % and 9.34 % out-of-sample annualized return. In addition, our results suggest that machine learning models should be provided with additional features about prior disclosures, while being trained on the ternary prediction problem that allows for predictions of neutral market reactions. We complement our results with several sensitivity analyses that show how profitability is influenced by transaction costs, different ensemble sizes, return neutrality thresholds, and liquidity filtering. Ultimately, we provide useful insights for practitioners by describing how the machine learning models arrive at decisions in terms of Shapley Additive Explanations. Collapse

Topics: shapley additive explanation accounting telephone electronic mail

Methods: machine learning sensitivity analysis term frequency–inverse document frequency GloVe random forest classification

Theories: transaction cost economics game 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

Effect of linguistic disfluency on consumer satisfaction: Evidence from an online knowledge payment platform

2023 | Information & Management | Citations: 0

Authors: Zhang, Jin; Li, Xinrui; Zhang, Jilong; Wang, Liye

Abstract: The popularity of online knowledge payment platforms enables online users to dis ... Expand

Abstract: The popularity of online knowledge payment platforms enables online users to disseminate paid knowledge via voice communication. However, such communication provided by users with little professional teaching skills commonly tends to contain linguistic disfluency, which is a potential determinant of consumer satisfaction of paid knowledge products. This study examines how linguistic disfluency inherent in paid knowledge products impacts consumer satisfaction and the moderating effects of two consumer knowledge aspects, namely expertise and familiarity. Based on processing fluency theory, we build a theoretical model to illuminate relationships between consumer satisfaction, linguistic disfluency, and consumer knowledge. Leveraging data from Zhihu Live, a leading online knowledge payment platform, we find that linguistic disfluency is negatively associated with consumer satisfaction; nevertheless, this negative association disappears or turns into a positive effect for con­ sumers with high expertise and low familiarity. Our study offers implications for platforms to accomplish high consumer satisfaction and further improve user retention and revenue. Collapse

Topics: consumer behavior logistics management electronic business knowledge base absorptive capacity

Methods: regression analysis method doc2vec robustness check ordinary least square cross sectional research

Theories: processing fluency theory

Exploiting Expert Knowledge for Assigning Firms to Industries: A Novel Deep Learning Method

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Zhao, Xiaohang; Fang, Xiao; He, Jing; Huang, Lihua

Abstract: Industry assignment, which assigns firms to industries according to a predefine ... Expand

Abstract: Industry assignment, which assigns firms to industries according to a predefined industry classification system (ICS), is fundamental to a large number of critical business practices, ranging from operations and strategic decision-making by firms to economic analyses by government agencies. Three types of expert knowledge are essential to effective industry assignment: definition-based knowledge (i.e., expert definitions of each industry), structure-based knowledge (i.e., structural relationships among industries as specified in an ICS), and assignment-based knowledge (i.e., prior firm-industry assignments performed by domain experts). Existing industry assignment methods utilize only assignment-based knowledge to learn a model that classifies unassigned firms to industries, overlooking definition-based and structurebased knowledge. Moreover, these methods only consider which industry a firm has been assigned to, ignoring the time-specificity of assignment-based knowledge, i.e., when the assignment occurs. To address the limitations of existing methods, we propose a novel deep learning-based method that not only seamlessly integrates the three types of knowledge for industry assignment but also takes the timespecificity of assignment-based knowledge into account. Methodologically, our method features two innovations: dynamic industry representation and hierarchical assignment. The former represents an industry as a sequence of time-specific vectors by integrating the three types of knowledge through our proposed temporal and spatial aggregation mechanisms. The latter takes industry and firm representations as inputs, computes the probability of assigning a firm to different industries, and assigns the firm to the industry with the highest probability. We conduct extensive evaluations with two widely used ICSs and demonstrate the superiority of our method over prevalent existing methods. Collapse

Topics: innovation management electronic finance industry 4.0 database system

Methods: support vector machine deep learning doc2vec experiment computational algorithm

Mining longitudinal user sessions with deep learning to extend the boundary of consumer priming

2022 | Decision Support Systems | Citations: 0

Authors: Cheng, Li-Chen; Chen, Kuanchin

Abstract: Priming is challenging when consumers start shortlisting products before the fin ... Expand

Abstract: Priming is challenging when consumers start shortlisting products before the final purchase. This is because this shortlisting process is performed in multiple user sessions online across time, the shortlist does not stay as a static list, and product comparison in this stage uses the heuristics internal to individual consumers. The goal of this study is two folds: (1) to approximate user heuristics after B&B product shortlisting using NLP and deep learning techniques, and (2) to identify optimized deep learning models for the representation of key elements of con­ sumer heuristics. This offers an extension of the priming theory into product comparison and shortlisting stages that were traditionally difficult for marketers to tap into. By analyzing the B&B product information repeated visited in user sessions, the formation of shortlists is identified and products in the shortlists can then be compared. Subsequent priming and promotions can therefore be performed closer to the actual purchase. Our study also provides marketers keywords and their associated activated words relevant for crafting marketing messages. As these activation words are extracted from the B&B sites and product reviews that the users had visited repeatedly in long-term tracking sessions, they are analogous to effects produced from user participatory design, an approach popular in the IT world. Our work shows that opportunities for marketing decision support, especially into the shortlisting phase, are now possible through machine learning techniques. Both theoretical and practical implications are provided. Collapse

Topics: recommender system marketing management user behavior word of mouth online word of mouth

Methods: deep learning natural language processing doc2vec BERT product review

Theories: marketing theory