Abstract

     Mental health research through data-driven methods has been hindered by a lack of standard typology and scarcity of adequate data. In this study, we leverage the clinical articulation of depression to build a typology for social media texts for detecting the severity of depression. It emulates the standard clinical assessment procedure Diagnostic and Statistical Manual of Mental Disorders (DSM-5) and Patient Health Questionnaire (PHQ-9) to encompass subtle indications of depressive disorders from tweets. Along with the typology, we present a new dataset of 40191 tweets labeled by expert annotators. Each tweet is labeled as ‘non-depressed’ or ‘depressed’. Moreover, three severity levels are considered for ‘depressed’ tweets: (1) mild, (2) moderate, and (3) severe. An associated confidence score is provided with each label to validate the quality of annotation. We examine the quality of the dataset via representing summary statistics while setting strong baseline results using attention-based models like BERT and DistilBERT. Finally, we extensively address the limitations of the study to provide directions for further research.

Introduction

     Analyzing the presence of mood and psychological disorders through behavioral and linguistic cues from social media data remains a critical area of interdisciplinary research. In addition to these disorders, the last decade has seen exponentially increasing attempts to assess related symptomatology such as depressive disorders, self-harm, and severity of mental illness using non-clinical data (Bucci et al., 2019). Social media platforms and other online discussion forums have been particularly appealing to the research community for various research purposes (e.g., population-level mental health monitoring (Conway & O’Connor, 2016), personal traits detection (Marouf et al., 2020), cyberbullying spotting (Bozyiğit et al., 2021), etc.) because of the massive scale of data. This massive data flow has resulted from increasing rates of internet access and people spontaneously sharing their suffering, pain, and struggle anonymously on these platforms (Ofek et al., 2015). Recognizing the early symptoms of depressive disorder through a person’s language use can prevent many disastrous outcomes like self-harm, suicide, etc., and even help deploy effective treatment in proper time. Moreover, the outbreak of the COVID-19 pandemic is likely to have devastating impacts on the mental health of millions of individuals as lockdown in the affected areas has reported high rises in the incident rates of mood disorder, including acute stress disorder, post-traumatic stress disorder, generalized anxiety disorder, and overall sub-clinical mental health deterioration (Singh et al., 2020). The scope of mental health deterioration during the COVID-19 pandemic and the comprehensive nature of diagnosing depressive disorders have provided an unprecedented need to infer the mental states of individuals from all-inclusive resources. Recent studies have revealed that valuable insights into the impact of the pandemic on population-level mental health can be inferred from posts or comments on social media (Low et al., 2020).

Conclusions and future work

     This work introduced a new typology for diagnosing depression severities from social media texts, as well as a unique dataset of labeled tweets with a confidence score for each label. The dataset was constructed based on strong ground truths and clinical validation, and it is expected to help alleviate the scarcity of mental health data to some extent. The description of the process and challenges in creating such a dataset may motivate researchers to collect similar corpora of this scale from other social media and discussion forums. The experimental results indicated that existing state-of-the-art models often fail to understand the contextual undertone of the data samples. Developing a model that is capable of comprehending the subdued relationship and differences among depression severities can result in an even better understanding of human cognition. Moreover, analysis of the classification performance indicates that there is no distinct division of keywords among different depression severities. The same keyword might be used differently to express different emotions, rather it is more important to understand the context of the tweet to diagnose the severity of depression. Broader implications of this research may include personalizing and directing preventative and awareness messages by health professionals to the users in need.

Abstract

Open Access and Permissions

Share and Cite

Article Metrics

Author Biographies

Order Article Reprints

Big data analytics is one high focus of data science and there is no doubt that big data is now quickly growing in all science and engineering fields. Big data analytics is the process of examining and analyzing massive and varied data that can help organizations make more-informed business decisions, especially for uncover hidden patterns, unknown correlations, market trends, customer preferences, and other useful information. Big data has become essential as numerous organizations deal with massive amounts of specific information, which can contain useful information about problems such as national intelligence, cybersecurity, biology, fraud detection, marketing, astronomy, and medical informatics. Several promising machine learning techniques can be used for big data analytics including representation learning, deep learning, distributed and parallel learning, transfer learning, active learning, and kernel-based learning. In addition, big data analytics demands new and sophisticated algorithms based on machine learning techniques to treat data in real-time with high accuracy and productivity.

The papers published in this Special Issue (Machine Learning Technologies for Big Data Analytics) have covered various vital topics enriching the state of the art in artificial intelligence, machine learning, and big data analytics. Additionally, these search papers build upon the fundamental techniques and approaches accomplished earlier. The creativity in the established papers resides in the methods, reviews, and experimental techniques that present an outstanding value for beneficial applications. That presents one of the explanations for why this Special Issue has been named “Machine Learning Technologies for Big Data Analytics”. Nevertheless, there is another explanation: practical applications need researchers, scientists, and engineers to find solutions for the big data problems consistent with current technologies and react to the demands from the near future. That is why the searchers must utilize and develop artificial intelligence and machine learning methods for a specific need. The reader will see this Special Issue as valuable for that goal.

Abstract

     In parallel with the development of information and network technology, large amounts of data are being generated by the Internet, and data-driven methodologies are now often being used in decision-making. Recent studies have investigated personalized individual semantics (PIS) in various decision-making contexts to model a fact that words mean different things to different people. However, few studies have investigated PIS in the context of multi-attribute decision-making (MADM). In MADM, in addition to multi-attribute linguistic information, pre-existing classification of the alternatives is always present, which have not been considered in prior research. Most previous studies have simply demonstrated the feasibility of PIS methods with numerical examples using small-scale models, and not with realistic datasets. Therefore, in this study, we propose a data-driven learning model to analyze the PIS of decision makers to support a multi-attribute decision-making model that considers pre-existing classification of the alternatives. Specifically, we first propose a PIS multi-attribute learning function to define a general computation form for comprehensive evaluation of the value of alternatives. Then, considering this pre-existing classification of the alternatives, a PIS learning model is constructed by analyzing the relations between calculated values of alternatives and corresponding class assignments to obtain personalized numerical scales of linguistic terms for a decision maker. Finally, we present a case study based on two datasets and a comparison with other methods to justify the feasibility of the proposed model.

Introduction

     Multi-attribute decision-making (MADM) involves an individual or a group of decision makers selecting an option by evaluating a set of alternatives according to multiple attributes [1,2,3,4]. In realistic MADM problems, decision makers often prefer to use language and linguistic terms to express their preferences for evaluating the objects or alternatives, and such information is conventionally included in multi-attribute linguistic decision matrices to represent their preferences [5].

     This means there is a need for computing with words (CWW) [6,7] when dealing with linguistic preferences in decision making. Obviously, words mean different things to different people [8,9], and type-2 fuzzy sets [8] are commonly used to deal with this issue in CWW. The CWW model of type-2 fuzzy sets is a useful tool to deal with multiple meanings, but this model does not represent specific semantics for individuals. For example, if a family with three members wants to buy a car, perhaps the members of the family all think the car is “good”. However, the numerical decision-making meaning of the word “good” might be accurately represented as 0.9 for one member, and 0.7 for the other two members. This reflects PIS among the three members. Porro et al. [10] proposed the concept of perceptual maps to represent the differences between the decision makers’ semantics of linguistic terms in MADM. Recently, Li et al.

Conclusions

     In this study, considering the fact that words mean different things to different people, we propose a PIS learning method for DD-LMADM based on multi-attribute linguistic information and information on the classification of alternatives. The proposed model starts with a PIS multi-attribute learning function to provide a general computation form for evaluating the comprehensive values of alternatives in LMADM models; based on this function, we propose a data-driven PIS learning model that considers the distinct linguistic term sets and the unknown weights associated with the criteria to calculate the PNS of linguistic terms for decision makers.

     The practical examples with car evaluation datasets and house evaluation datasets illustrate the applicability of the proposed data-driven PIS learning approach. Furthermore, we compare our approach with the existing CWW methods based on a triangular membership function and a 2-tuple linguistic model in terms of the inconsistency between the calculated preference values of alternatives and their class assignment.

Abstract

     This study integrated multiple objective decision-making approaches including data envelopment analysis (DEA), rough set theory and TOPSIS method for exploring the competitiveness of pharmaceutical multinational enterprises. Firstly, this study applied an advanced two-stage network DEA to measure the R&D efficiency and business performance of pharmaceutical multinational enterprises (PMNEs) listed in the Forbes Global 2000 and ranked these PMNEs by using rough set theory, DEA and TOPSIS method. In addition, differences in environmental, social, and governance (ESG) performance across three continents were investigated. Findings show that North America is significantly the best (worst) region in terms of business performance (R&D efficiency) while Europe is significantly the best (worst) region in terms of R&D efficiency (business performance). Alfresa Holdings Corporation, a PMNE from Japan, is the only PMNE that is efficient from both an R&D and business performance perspective. European PMNEs have significantly better environmental and social performance than other regions, however, they have the worst governance performance. Overall, this study provides insights to managers and investors into the application of various methods for accurately measuring performance and ranking multinational enterprises.

Introduction

     The pharmaceutical industry is one of the most important and competitive industries in the world, it not only has a critical role in the health maintenance of individuals but also in economic growth (Sharma & Modgil, 2019). Pharmaceutical firms have spent a substantial proportion of their time and investment in research and development (R&D) (Rao, 2020). In 2018, R&D expenditure in the pharmaceutical industry was 179 billion U.S. dollars globally (Mikulic, 2020). A correct grasp of the R&D efficiency of the industry is required to improve resource allocation and thereby prevent either excess or shortage of resource inputs (Liu & Lyu, 2020). According to Lu et al. (2019), evaluating multiple indicators simultaneously is useful for appropriate decision-making. An overall efficiency can be decomposed into two stages of efficiencies (Kao & Hwang, 2008), suggesting that we should also evaluate the sub-processes of a firm (Kao & Hwang, 2011). That is, managers should evaluate their firm performance not only from a multidimensional perspective but also from those of its internal processes. As mentioned in the research of Sharma and Modgil (2019), business performance additionally depends on cost reduction of manufacturing operations and improving the firm’s innovative ability. Recently, Hsieh et al. (2020) have applied two-stage data envelopment analysis (DEA) to investigate organizations’ innovation and business performance by investigating the network structures of decision-making units (DMUs).

Conclusion

     This study measures the firm performance of 41 PMNEs from a two-stage perspective, namely R&D efficiency and business performance, by integrating a two-stage network DEA and SOCP technique. Moreover, this study integrates the DEA approach and rough set theory to rank PMNEs. The findings of this research can serve as a reference for managers of PMNEs in their decision-making process. Besides, we examine differences in the ESG scores of the PMNEs among different geographic regions (America, Asia, and Europe). This acts as a guide for investors, managers, and other stakeholders when attempting to move their ESG initiatives further.

     R&D performances in the operation of the observed PMNEs are not attracting enough attention. Alfresa Holdings Corporation is the only efficient PMNE for both R&D efficiency and business performance. North America is significantly the best (worst) region in terms of business performance (R&D efficiency) while Europe is significantly the best (worst) region in terms of R&D efficiency (business performance). From the perspective of ESG performance, European PMNEs significantly have better environmental and social performance than other regions whereas they are the worst concerning governance performance.

Abstract

1. Introduction

2. Literature review: conceptualising BDA and SCO

3. Research methodology

4. Empirical findings

5. Proposed framework

6. Discussion and implications

7. Conclusions

Disclosure statement

Notes on contributors

References

Abstract

     Undoubtedly, due to the increasingly competitive pressures and the stride of varying demands, volatility and disturbance have become the standard in today’s global markets. The spread of Covid-19 is a prime example of that. Supply chain managers are urged to rethink their competitive strategies to make use of Big Data Analytics (BDA), due to the increasing uncertainty in both demand and supply side, the competition among the supply chain partners and the need to identify ways to offer personalised products and services. With many supply chain executives recognising the need of ‘improving with data’, supply chain businesses need to equip themselves with sophisticated BDA methods/techniques to create valuable insights from big data, thus, enhancing the decision-making process and optimising the efficiency of Supply Chain Operations (SCO). This paper proposes the building blocks of a theoretical framework for understanding the impact of BDA on SCO. The framework is based on a Systematic Literature Review (SLR) on BDA and SCO, underpinned by Task-Technology-Fit theory and Institutional Theory. The paper contributes to the literature by building a platform for future work on investigating factors driving and inhibiting BDA impact on SCO.

Introduction

     Over the past decade, the manufacturing sector has been in the midst of a fourth wave of technological advancement (Rüßmann et al. 2015). During this, a plethora of manufacturing and supply chain businesses have transformed their operations into intelligent/smart manufacturing. This is by adopting a variety of innovative technologies such as autonomous robots, simulations, horizontal and vertical systems integration, internet of things [IoT], cybersecurity, cloud services, additive manufacturing, and most importantly, big data analytics (Wamba et al. 2020). Several noticeable researchers and practitioners have recognised the significance and applicability of Industry 4.0 (I_4.0) for operations, logistics and production management at large (Sivarajah et al. 2017; Rahman et al. 2022). However, relatively little is known about the impact of BDA on SCO – particularly focussing on the five dimensions of SCO: demand planning, production and manufacturing, logistics, procurement, and inventory. Among the extant research studies published, a few shed light on the link between IoT and SCO (e.g. Ben-Daya, Hassini, and Bahroun 2019) and the impact of additive manufacturing on SCO, processes and performances (e.g. Li, Tang, et al. 2017).

Conclusions

     Arguably, SCO and BDA can enable the dynamic capabilities of firms, allowing decision makers to enhance the corporate or company abilities or to better sense emerging opportunities and threats. This paper presents the past trends and current state of BDA research published specifically in the context of SCOs and its respective dimensions. We proposed a conceptual framework based on two research questions: Investigating the benefits of implementing BDA methods/techniques to achieve better decision-making for SCO? and Investigating the benefits of implementing BDA methods/techniques in achieving optimisation of SCOs? The continuing interest and the use of BDA specifies that in future research studies academics, researchers and practitioners may focus on the factors driving and inhibiting BDA to further propose robust solutions to the service related problems. The intention in conducting this detailed investigation was to provide a useful and yet usable source of information for future researchers. The discussion also highlighted several research limitations and future directions for BDA applications within the SCO research area to catalyse the research development of the topic.

Big data analytics has been widely regarded as a breakthrough technological development in academic and business communities. Despite the growing number of firms that are launching big data initiatives, there is still limited understanding on how firms translate the potential of such technologies into business value. The literature argues that to leverage big data analytics and realize performance gains, firms must develop strong big data analytics capabilities. Nevertheless, most studies operate under the assumption that there is limited heterogeneity in the way firms build their big data analytics capabilities and that related resources are of similar importance regardless of context. This paper draws on complexity theory and investigates the configurations of resources and contextual factors that lead to performance gains from big data analytics investments. Our empirical investigation followed a mixed methods approach using survey data from 175 chief information officers and IT managers working in Greek firms, and three case studies to show that depending on the context, big data analytics resources differ in significance when considering performance gains. Applying a fuzzy-set qualitative comparative analysis (fsQCA) method on the quantitative data, we show that there are four different patterns of elements surrounding big data analytics that lead to high performance. Outcomes of the three case studies highlight the inter-relationships between these elements and outline challenges that organizations face when orchestrating big data analytics resources.

Introduction

We are living in the “Age of Data”, with new data being produced from all industries and public bodies at an unprecedented, and constantly growing rate (McAfee, Brynjolfsson, & Davenport, 2012). As a result, there has been a great hype which has led organizations to make substantial investments in their quest to explore how they can use their data to create value (Constantiou & Kallinikos, 2015). The main premise big data analytics builds on is that by analyzing large volumes of unstructured data from multiple sources, actionable insights can be generated that can help firms transform their business and gain an edge over their competition (Chen, Chiang, & Storey, 2012). Being able to obtain such data-generated insight are particularly relevant, especially for organizations that operate in dynamic and high-paced business environments, where making informed decisions is critical (Wamba et al., 2017).

Data analytics has become an increasingly eye-catching practice in both the academic and the business communities. The importance of data analytics has also prompted growing literature to focus on the design of data analytics. However, the boundary conditions for data analytics in creating value have been largely overlooked in the literature. The objective of this article therefore is to examine the business value of data analytics usage and explore how such value differs in different market conditions. We rely on an online B2C platform as our empirical setting and obtain several important insights. First, both demand-side and supply-side data analytics usage has a positive effect on the performance of merchants. Second, when merchants’ product variety is high, the influence of usage toward demand-side data on performance is strengthened, whereas such impact is weakened for supply-side data analytics. Third, when competitive intensity is high, the performance implication of demand-side data analytics usage is strengthened, whereas such impact is not strengthened for supply-side data analytics. This study contributes by advancing the overall understanding of business value of data analytics.

Introduction

With dramatic advancement in data collecting, storage, and processing technologies in recent decades, organizations worldwide are exploring new data-enabled ways to compete and win—transforming themselves to take advantage of the vast array of available data to improve decision-making and performance [1–3]. These new opportunities have led many managers to rely less on business decision-making process and more on data itself in their decision-making [4,5]. Data analytics, therefore, has become an increasingly eye-catching practice in both academic and the business communities, and industry studies have highlighted this significant development. For example, on the basis of a survey of over 4000 information technology (IT) professionals from 93 countries and 25 industries, the IBM Tech Trends Report [6] identified business analytics as one of the four major technology trends in the 2010s. In a survey of the state of data analytics by Bloomberg Businessweek [7], 97% of companies with revenues exceeding US$100 million were found to use some form of data analytics [8]. The importance of data analytics has also prompted growing literature to focus on the design of data analytics for generating knowledge and intelligence to support decision-making and strategic objectives [3,9,10]. For example, Bardhan et al. [11] demonstrated that using health IT-related data could help hospitals save millions of dollars by avoiding costly readmission-related penalties. Martens et al. [9] examined the use of massive, fine-grained data on consumer behavior to improve predictive models for targeted marketing. Guo et al. [3] proposed a system framework for extracting representative information from intra-organizational blogging platforms. The puzzle, however, is why not all firms have implemented this practice? The stream of IT business value research points that value creation process of technological innovations in a firm cannot depart from how to use them [12,13]. For example, Devaraj and Kohli [14] posited and proved that the actual usage of technology is a key variable to explain the impact of IT application on organizational performance.

Introduction

The health industry is undergoing enormous transformations with the pressure to reduce costs and improve the quality and efficiency of healthcare services (Wu, Kao, & Sambamurthy, 2016). The exponential growth of health data, the pressures to make continuous investments and the necessity to provide integrated care services meeting the healthcare needs of patients, are all good reasons for Hospital Information Systems adopt Data Analytics (DA) and thus, ensure reliable and efficient services. This situation becomes even more demanding because this enormous volume of health data does not only come from traditional interviews, hospitalizations, and medical tests in a hospital or outpatient clinic, but it involves data that patients collect themselves using wearables for telemonitoring and data that healthy people collect using a wide variety of health and wellbeing apps (Roesems-Kerremans, 2016). In addition, the emergence of new technologies followed by genetic information, has contributed to the increase of clinical data collected. Process and analyse all this information, allows to identify health patterns that can contribute to cure and prevention of diseases, besides improving patient safety and quality of life. In short, improving the efficiency, quality and savings of health systems. Therefore, new opportunities are emerging based on the rapid evolution of Big Data technologies and the enormous availability of data that organizations can capture (Raguseo, 2018). Data management and Analytics is critical in health information systems. Data management includes processes and technologies to acquire, store, prepare and retrieve data for analysis. Analytics, refers to techniques used to analyse and acquire intelligence from Big Data (Gandomi & Haider, 2015). The investigation suggests that organizations using DA, when managing decision-making processes, are more productive and profitable than those who do not (Mathews, 2015). However, it is not clear at the moment, to what extent organizations are already implementing Analytics, as there are still many challenges in this area (Lismont, Vanthienen, Baesens, & Lemahieu, 2017). In this sense, organizations that intend to increase the use of DA to optimize costs, profitability, productivity and quality should consider strategic investments in this field. Healthcare organizations are clearly no exception to this rule. Within the healthcare field, Hospitals have followed three stages of data computerization and management, namely: data collection, data sharing and (more recently and gradually) data analysis (Sanders, Burton, & Protti, 2013). The collection, storage and analysis of health data have been, are and will remain, fundamental procedures to providing efficient healthcare services, and their importance is increasing in line with the growing amount of health data collected every day (Roesems-Kerremans, 2016).

Abstract

This paper investigates big data analytics research and application in supply chain management between 2010 and 2016 and provides insights to industries. In recent years, the amount of data produced from end-to-end supply chain management practices has increased exponentially. Moreover, in current competitive environment supply chain professionals are struggling in handling the huge data. They are surveying new techniques to investigate how data are produced, captured, organized and analyzed to give valuable insights to industries. Big Data analytics is one of the best techniques which can help them in overcoming their problem. Realizing the promising benefits of big data analytics in the supply chain has motivated us to write a review on the importance/impact of big data analytics and its application in supply chain management. First, we discuss big data analytics individually, and then we discuss the role of big data analytics in supply chain management (supply chain analytics). Current research and application were also explored. Finally, we outline the insights to industries. Observations and insights from this paper could provide guideline for academia and practitioners in implementing big data analytics in different aspects of supply chain management.

نمونه ترجمه

 چکیده: ما در این مقاله به بررسی داده های کلان پژوهش تحلیلی و کاربرد آن در مدیریت زنجیره تامین بین سالهای ۲۰۱۶-۲۰۱۰ می پردازیم و بینش هایی را برای صنایع فراهم می آورد . در سالهای اخیر افزایش بسیار زیادی در میزان داده هایی که از طریق شیوه های مدیریت و زنجیره تامین جامع ایجاد شده اند وجود داشته است . علاوه بر این در این محیط پر رقابت ؛متخصصان زنجیره ی تامین در تلاش هستند تا این حجم عظیم از داده ها را مدیریت کنند. و همچنین در حال بررسی تکنیک های جدیدی هستند تا اقدام به بررسی اینکه این داده ها چگونه ایجادشده اند به چه شکل به دست آمده اند و به چه طریقی سازماندهی و تجزیه و تحلیل شده اند ؛ نمایند تا اینکه بتوانند بینش های ارزشمندی را به صنایع ارائه نمایند. تجزیه و تحلیل داده های کلان یکی از بهترین تکنیک هایی است که می تواند به آنان در غلبه کردن بر مشکلاتشان یاری رساند. آگاهی از مزایای امیدوارکننده ی تجزیه و تحلیل داده های کلان در زنجیره ی تامین به ما این انگیزه را داده است تا به نگارش این مقاله درباره اهمیت و تاثیر داده های کلان و کاربرد آن در مدیریت زنجیره ی تامین اقدام نماییم . در ابتدا؛ بصورت جداگانه درباره تجزیه و تحلیل داده های کلان بحث می کنیم و سپس درباره ی نقشی که تجزیه و تحلیل داده های کلان در مدیریت زنجیره ی تامین ایفا میکننده بحث می کنیم . همچین تحقیقات فعلی و کاربرد مورد بررسی قرار گرفتند. ودر پایان به تشریح بینش ها برای صنایع پرداختیم . مشاهدات و بینش های حاصل از این مقاله می توانندراهنمایی هایی را برای دانشگاهیان و کارورزان به منظور عملیاتی کردن تجزیه و تحلیل داده های کلان در ابعاد مختلف مدیریت زنجیره تامین را فراهم آورند.