The proliferation of cost-effective sensors and devices which continually generate data as well as the ecosystem of tools and software applications has led to the term concept of big data. Although the concept does not have a precise definition, it captures the idea of a field that confronts data, both structured and non-structured that is too large or too complex to process by conventional means. This definition captures the idea that big data is a field which tackles a challenge and which will perpetually need to develop new tools and algorithms. Trying to understand big data is of paramount importance to our current society, as the number of data-generation systems is exponentially increasing and affects our capability to effectively manage the knowledge that could be extracted from it. New knowledge management systems are being developed to handle the complexity of big data systems. The so-called three Vs that initially characterised big data: Volume, Velocity and Variety were recently extended to include other Vs like Viability or Value. Viability is an important aspect of big data deployments which must take into account which aspects are affordable for a given domain. It is not enough to recognise that a problem requires big data technologies, it is necessary to assess which aspects can be handled with the available services and applications, taking into account the local idiosyncrasies which can be affected policy-makers and strategic innovation actions. Value is the most important aspect to take into account in this context. Big data solutions are adopted at the same time as digital transformation is being stimulated, which can increase the value of those investments.
The emphasis of this special issue is on the behavioural aspects of big data, exploring the relation of Behaviour, Big Data and Social Mining towards the deeper understanding of the evolution of the human collective behaviour and wisdom, with a special emphasis on users.
The special issue will focus on the research, services and applications related to big data and its implications for policy development and technology transfer. In addition, the special issue will prefer a focus on relevant topics related to users rather than on artificial intelligence, business, marketing or general discussions of big data and knowledge society.
The Special Issue ‘Big data research for behaviour, integrating services and applications: Implications for innovation, policy making and technology transfer’ has a collection of 10 outstanding papers that discuss key issues.
The first paper, titled ‘The Influence of ICT-Driven Innovation: A Comparative Study on National Innovation Efficiency Between Developed and Emerging Countries’ (by Xiaojiong Wang and Chao Zhang) states that ‘in the big data era, Information and Communication Technology (ICT), including the Internet and sensors, digitises physical activity extensively. This leads to the development of ICT Driven Innovation (IDI) which may has a strong influence on National Innovation Efficiency (NIE). The purpose of this paper is to provide insights into the impact of IDI on NIE in both advanced and emerging countries. Data Envelopment Analysis (DEA) is employed to obtain the individual score for each country. We focus on comparing IDI between advanced and emerging economies in particular. We believe that IDI is an important reason why the average NIE score is higher in developed countries than in emerging countries. Obviously, developed countries have shown good capabilities in IDI in excess of most emerging countries. This includes but is not limited to R&D expenditure across the ICT industry, ICT patents, etc. Several emerging economies received high NIE scores such as China and Brazil, who also have a good performance in IDI. On this basis, we discuss the mechanism of how IDI affects NIE. ICT industry innovation, non-ICT industries innovation, and ICT infrastructure are summarised as the primary factor affecting NIE by IDI. Further empirical research is required in the future’.
The second paper, titled ‘Analysis of Tweets About Football: 2013 and 2018 Leagues in Turkey’ (by Nihat Kasap, Selcen Ozturkcan, Altug Tanaltay and Mesut Ozdinc), affirms that ‘football has recently developed into a unique sector with complex management and marketing functions, where novel communication technologies are employed. In this paper, we aim to contribute to the numerous fields involving emerging European sports marketing literature, social media analytics, and digital consumer behaviour. Our purpose is to explore Twitter use related with football by analysing real-time streamed data in offering a longitudinal perspective by focusing on 2013 and 2018 leagues in Turkey via the use of social media analytics framework. Retrieved dataset involved randomly selected publicly available 370 thousand and 6.8 million real-time tweets in 2013 and 2018 leagues, respectively. We report that majority of tweets about the football was posted within the three-hour window before the match independent of the match result and the importance of the result. Moreover, prematch tweeting volume was almost a crystal ball signalling match winning. Our findings are valuable for sports managers and marketers where some key suggestions provided are to involve particular contexts of winning or losing in their after-match marketing plans, to value weekdays as much as the weekends, and to utilise the afterwork prime time of social media engagement’.
The third paper, titled ‘Opera-Oriented Character Relations Extraction for Role Interaction and Behaviour Understanding: A Deep Learning Approach’ (by Peiquan Jin, Xinnan Dai, Xujian Zhao, Xuebo Cai, Hui Zhang, Chunming Yang and Bo Li), proposes that ‘there are a great number of complex relations among different characters in an opera. Retrieving such relations is crucial for performers and audience to accurately understand the features and behaviour of roles. Aiming to automatically extract relations among characters in an opera, in this paper we propose an effective method that can extract character relations from opera scripts. Firstly, we construct a uniform reasoning framework for opera scripts. Based on this model, we propose a deep syntax-parsing method to detect character relations from opera scripts. After that, we propose a new deep learning approach called SL-Bi-LSTM-CRF to extract the objects involved in character relations. The proposed SL-Bi-LSTM-CRF algorithm is a sentence-level relation extraction algorithm based on the bi-directional LSTM with a CRF layer. With this mechanism, we are able to get a detailed description for character relations. We conduct experiments on a real dataset of opera scripts. The experimental results in terms of precision, recall, and F-score suggest the effectiveness of our proposal’.
The fourth paper, titled ‘Examination of the Effects of Computer-Based Mathematics Instruction Methods in Children with Mathematical Learning Difficulties: A Meta-Analysis Study’ (by Kazim Kucukalkan, Mehmet Beyazsacli and Aysegul Oz) explores ‘the effects of Computer-Based Instruction(CBI) on learning of children with mathematical learning difficulties by evaluating the results of studies conducted in different countries with meta-analysis method which is defined as a subset of systematic reviews of experimental researches. Certain criteria have been used to determine which ones of the examined studies would be included in meta-analysis. Selecting articles and thesis published between the years of 2007–2018, forming the sample group from children with mathematical learning difficulties, selecting the sample group from children studying in primary schools, significance level of data, inclusion of standard deviation and sample size constitute the ground of the criteria. The sample size of the study is 1364 for experimental group and 926 for control group. Consequently, it has been observed that Computer-Based Instruction (CBI) had positive effects on learning of children with mathematical learning difficulties’.
The fifth paper, ‘The “Who” and the “What” in International Migration Research: Data-Driven Analysis of Scopus-Indexed Scientific Literature’ (by Saeed-Ul Hassan, Anna Visvizi and Hajra Waheed) discusses ‘debates pertaining to international migration (IM) as depicted by cross-disciplinary records collected in Scopus, thus making a case for the value added of bibliometric analysis and new ways of its application. Specifically, to gain a thorough understanding of issues, names, and topics that have contributed to the IM debate since 1963, bibliometric analysis was conducted on 12,663 procured records. The findings suggest that regardless of the depth and breadth of the analysis, it is doomed to remain partial. That is, when confronted with academic work not available in Scopus, this study concludes that more work needs to be done to ensure, on the one hand, interoperability of research data repositories, and on the other hand, synergies among the until now divided research-communities. Only in this way, it is argued, will it be possible to ensure transparency of research artefacts, identify issues and problems silenced and/or under-researched in the field, and finally enable more efficient dialogue between academia and decision-makers, including international organisations’.
The sixth paper titled ‘Big Data and IoT Solution for Patient Behaviour Monitoring’ (by Kwok Tai Chui, Ryan Wen, Liu, Miltiadis Lytras and Mingbo Zhao) states that ‘the study of patient behaviours (vital sign, physical action and emotion) is crucial to improve one’s quality of life. The only solution for handling and managing millions of people’s behaviours and health would be big data and IoT technology because most of the countries are lack of medical professionals. In this paper, a big data and IoT based patient behaviour monitoring system has proposed. Qualitative studies are made carried out on the selected behaviours analytics, cardiovascular disease identification and fall detection. At last, authors have summarised the general challenges like trust, privacy, security and interoperability and as well as special challenges in various sectors: government, legislators, research institutions, information technology company companies and patients’.
The seventh paper, titled ‘Applying Big Data and Stream Processing to the Real Estate Domain’ (by Herminio García-González, Daniel Fernández-Álvarez and Jose Emilio Labra and Patricia Ordóñez de Pablos) develops ‘an architecture that combines Big Data and Stream Processing which can be applied to the Real State Domain. Our approach consists of a specialisation of Lambda architecture and it is inspired by some aspects of Kappa architecture. As a proof of this solution we show a prototype developed following it. Finally, we highlight the differences between the proposed architecture and similar ones and draw some future lines following the present approach’.
The eighth paper, titled ‘An Adaptive Doctor Recommender System’ (by Ali Saud, Muhammad Waqar, Muhammad Nadeem Majeed, Hassan Dawood and Naif Aljohani) develops a ‘hybrid doctor recommender system, by combining different recommendation approaches: content base, collaborative and demographic filtering to effectively tackle the issue of doctor recommendation. The proposed system addresses the issue of personalisation through analysing patient’s interest toward selecting a doctor. It proposes a novel adoptive algorithm, which is used to construct a doctor’s ranking function. Moreover this ranking function is used to translate patients’ criteria for selecting a doctor into a numerical base rating, which will eventually be used in recommendation of doctors’.
The ninth paper, titled ‘Integrating TTF and IDT to Evaluate User Intention of Big Data Analytics in Mobile Cloud Healthcare System’ (by Shu Lin Wang and Shin I Lin) use big data analysis and a mobile cloud healthcare system to ‘aids young users in preventive healthcare against diabetes. It also integrates the Task-Technology Fit (TTF) and Innovation Diffusion Theory (IDT) models to evaluate user intentions to use the system, and tests this model using data collected from 374 young people. Results show that task-technology fit is significantly affected by task characteristics and technology characteristics, and also user intention of using the Big Data-based Mobile Cloud Healthcare system is affected by task-technology fit, perceived ease of use, and relative advantage. However, observability has no significant effect on user intentions of using the mobile cloud healthcare system. These findings provide some theoretical insights into the usage of the mobile cloud healthcare system’.
And the last paper of the special issue, titled ‘Sentiment Mining in Collaborative Learning Environment: Capitalising on Big Data’ (Rabindra Jena) aims to explore ‘the academic data using different efficient machine learning algorithms. The contribution of this paper is two-fold: (i) study the sentiment polarity (positive, negative, and Neutral) from students’ data using machine learning techniques and (ii) modelling and prediction of students’ emotions (Amused, Anxiety, Bored, Confused, Enthused, Excited, Frustrated, etc.) using the big data frameworks. The developed sentiment mining techniques using big data framework can be scaled and made adaptable for the source variation, velocity and veracity to maximise value mining for the benefit of students, faculties and other stakeholders’.
