Data Mining Practices Research Articles

Using Deductive Reasoning to Identify Unhappy Communities

The complex interplay between media and population sentiment is a well-known, yet hard to model, phenomenon. The extrema of individual sentiment (euphoria and depression) are known to be correlated with people’s social interaction, including activity in forums and social-media sites. Yet causality direction of this correlation still requires scrutiny and scientific analysis. The difficulty of such analysis comes, first and foremost, from the complexity of sentiment quantification. It is even more difficult to measure a shared sentiment of a community, due to the echo chamber effect. In addition, media analysis presents its own computational challenges, which were insurmountable until recent times, when we have been presented with unprecedented technical possibilities for quantification of community sentiment and its factors at a level of granularity never seen before. Behavioral psychology suggests that people’s behavior can be used as a measurable proxy for their sentiment. Behaviorist theory has been enhanced with the proliferation of targeted advertising and marketing science in the corporate world, and a number of phenomena connecting people’s sentiment and social behavior have been explained using behavioral psychology. In addition, advances in the theory and practice of data mining and machine learning have enabled non-empirical approaches to quantitative sociological analysis and development of new indicators of communal well-being that rely on the analysis of historical data. These considerations make it possible to investigate the interactions between media sentiment and community. This is the theme of the present submission.

Deploying data mining techniques to gain deeper insight into Nigerian customers' financial activities

Presently, Nigerian banks issue account statements in a tabular flat form. These statements mainly show basic logs of credit and debit transactions. They do not offer a deeper insight into the pure nature of transactions. Moreover, they lack rich mine-able data, and rather contain basic data tables that do not provide enough insights into customers' monthly/weekly/yearly expenses and earnings. In today’s fast-paced digital world, where information processing methods are rapidly changing, customers need not just a basic table of transactions but deeper analysis and detail report of their finances. This paper aims at identifying and addressing these problems by deploying data mining techniques and practices in building an application that helps customers gain a deeper insight and understanding of their spending and earnings over a particular period. Some of the techniques used are classification, statistical analysis, visualization, report generation and summarization.
 Keywords: Data mining, API, Anomaly Detection, GTBank, CBN, Bank statements, Nigeria

Smartphone sensing for understanding driving behavior: Current practice and challenges

• Understanding of driving behavior based on smartphone data is the core of the paper. • An inclusive 4-step methodological framework is established for driving analytics. • The 4 steps are: Data collection, data mining, modeling and decision making. • Challenging tasks of the proposed framework are extensively discussed. Understanding driving behavior – even in the rapid emergence of automation - remains in the spotlight, for decomposing complex driving dynamics, enabling the development of user-friendly and acceptable autonomous vehicles and ensuring the safe co-existence of autonomous and conventional vehicles on the road. Mobile crowdsensing has emerged as a means to understand and model driving behavior. Although the advantages of collecting data through smartphones are many (speed, accuracy, low cost etc.), the challenges including, but do not limited to, the preparation rate, the processing needs, as well as the methodological, legislative and security issues, are significant. The present paper aims to review the research dedicated to analyzing driving behavior based on smartphone sensors’ data streams. We first establish an inclusive stepwise framework to describe the path from data collection to informed decision making. Next, the existing literature is thoroughly analyzed and challenges in relation to data collection and data mining practices are critically discussed placing particular emphasis on the limitations and concerns regarding the use of mobile phones for driving data collection, as well as using crowd sensed data for feature extraction. Subsequently, modeling driving behavior practices and end-to-end solutions for driver assistance and recommendation systems are also reviewed. The paper ends with a discussion on the most critical challenges arising from the literature and future research steps.

Data Breaches and Potemkin Privacy: How FTC Regulation Can Restore Authority and Agency to Online Users and Destroy the Data Oligarchy

Data Breaches and Potemkin Privacy: How FTC Regulation Can Restore Authority and Agency to Online Users and Destroy the Data Oligarchy

Utilising learning analytics to support study success in higher education: a systematic review

Study success includes the successful completion of a first degree in higher education to the largest extent, and the successful completion of individual learning tasks to the smallest extent. Factors affecting study success range from individual dispositions (e.g., motivation, prior academic performance) to characteristics of the educational environment (e.g., attendance, active learning, social embeddedness). Recent developments in learning analytics, which are a socio-technical data mining and analytic practice in educational contexts, show promise in enhancing study success in higher education, through the collection and analysis of data from learners, learning processes, and learning environments in order to provide meaningful feedback and scaffolds when needed. This research reports a systematic review focusing on empirical evidence, demonstrating how learning analytics have been successful in facilitating study success in continuation and completion of students’ university courses. Using standardised steps of conducting a systematic review, an initial set of 6220 articles was identified. The final sample includes 46 key publications. The findings obtained in this systematic review suggest that there are a considerable number of learning analytics approaches which utilise effective techniques in supporting study success and students at risk of dropping out. However, rigorous, large-scale evidence of the effectiveness of learning analytics in supporting study success is still lacking. The tested variables, algorithms, and methods collected in this systematic review can be used as a guide in helping researchers and educators to further improve the design and implementation of learning analytics systems.

Implementing User Rights for Research in the Field of Artificial Intelligence: A Call for International Action

Last year, before the onset of a global pandemic highlighted the critical and urgent need for technology-enabled scientific research, the World Intellectual Property Organization ( WIPO) launched an inquiry into issues at the intersection of intellectual property ( IP) and artificial intelligence ( AI). We contributed comments to that inquiry, with a focus on the application of copyright to the use of text and data mining ( TDM) technology. This article describes some of the most salient points of our submission and concludes by stressing the need for international leadership on this important topic. WIPO could help fill the current gap on international leadership, including by providing guidance on the diverse mechanisms that countries may use to authorise TDM research and serving as a forum for the adoption of rules permitting cross-border TDM projects. Copyright law provides protection of the material interests of authors through rights to exclude certain uses of their works, including of their reproduction.1 At the same time, one of the universally accepted axioms of copyright law is that exclusivity should apply only to original expression, not to facts, ideas, procedures or methods of operation.2 It is also universally accepted that copyright contains free spaces to ensure follow-on creativity and to secure important fundamental rights and the public interest, in particular allowing research to be undertaken using protected material.3 We are far from an international consensus about how to give effect to the boundary between copyright and research rights in the context of text and data mining, machine learning, and artificial intelligence (AI). WIPO could play a vital constructive role in establishing a consistent international baseline that resolves potential tensions between copyright and text and data mining practices. It could also facilitate cross-border text and data mining research and collaboration. We explain these points in further detail below.

‘We’re Being Tracked at All Times’: Student Perspectives of Their Privacy in Relation to Learning Analytics in Higher Education

Higher education institutions are continuing to develop their capacity for learning analytics (LA), which is a socio-technical data mining and analytic practice. Institutions rarely inform their students about LA practices and there exist significant privacy concerns. Without a clear student voice in the design of LA, institutions put themselves in an ethical grey area. To help fill this gap in practice and add to the growing literature on students’ privacy perspectives, this study reports findings from over 100 interviews with undergraduate students at eight United States higher- education institutions. Findings demonstrate that students lacked awareness of educational data mining and analytic practices, as well as the data on which they rely. Students see potential in LA, but they presented nuanced arguments about when and with whom data should be shared; they also expressed why informed consent was valuable and necessary. The study uncovered perspectives on institutional trust that were heretofore unknown, as well as what actions might violate that trust. Institutions must balance their desire to implement LA with their obligation to educate students about their analytic practices and treat them as partners in the design of analytic strategies reliant on student data in order to protect their intellectual privacy.

Rhetoric, Torture, and Surveillance Time

Relying on select US government Torture Memos, this article develops the term “surveillance time” to highlight the ways in which surveillance practices, in this case within the material confines of post-9/11 detention centers, come to threaten humans’ subjectivities through temporal disruption and manipulation. While surveillance has lately been understood in digital terms, such as in corporations’ data-mining practices and in technologies like facial-recognition software, we should not neglect its material, embodied dimensions. Surveillance time ultimately asks us to reconsider how monitoring and information-harvesting practices blur the boundaries between human bodies and data. Attention to the relationship between torture and surveillance also opens up new possibilities for understanding the now-ubiquitous monitoring strategies integrated into everyday life.

Improved Cuckoo Optimization Algorithm for Association Rule Hiding

Association Rule Mining (ARM) is a standard data mining practice used to determine interactions hidden in huge sets. Association Rule Hiding (ARH) methods are used to preserve the privacy of data in ARM. ARH process modifies the original database without changing any non-sensitive rules and data. In order to hide the sensitive rules, cuckoo search optimization algorithm that was developed for hiding the sensitive association rules (COA4ARH) was proposed for sensitive rule hiding. In COA4ARH, number of transactions that should be modified to hide the sensitive rules is not considered which may leads to more number of iteration. In this paper, two properties are introduced to select less number of transactions to be modified. It makes the COA4ARH algorithm faster, decreases the number of lost rules and is suitable for variety of datasets. In order to increase the rule hiding capability of COA4ARH, new fitness functions are introduced. The new fitness functions reduce the amount of lost rules and avoid generation of ghost rules which are formed as objectives of COA4ARH algorithm. The multiple objectives in COA4ARH are conflicting with each other. This is known as multi-objective optimization problem. The multi-objective optimization deals with set of non-dominated solutions (Pareto front) for the problem having more than one objective. It is solved by using Crowding Distance (CD) which selects the optimal set of solution for association rule hiding. Thus, the proposed Improved COA4ARH- CD (ICOA4ARH-CD) can be suitable for variety of datasets and effectively hides the sensitive rules with fewer side effects.

Data Preprocessing: A preliminary step for web data mining

In recent years immense growth of data i.e. big data is observed resulting in a brighter and more optimized future. Big Data demands large computational infrastructure with high–performance processing capabilities. Preparing big data for mining and analysis is a challenging task and requires data to be preprocessed to improve the quality of raw data. The data instance representation and quality are foremost. Data preprocessing is preliminary data mining practice in which raw data is transformed into a format suitable for another processing procedure. Data preprocessing improves the data quality by cleaning, normalizing, transforming and extracting relevant feature from raw data. Data preprocessing significantly improve the performance of machine learning algorithms which in turn leads to accurate data mining. Knowledge discovery from noisy, irrelevant and redundant data is a difficult task therefore precise identification of extreme values and outlier, filling up missing values poses challenges. This paper discusses various big data pre–processing techniques in order to prepare it for mining and analysis tasks.

IDENTIFICATION OF “HUMAN ERROR” NEGATIVE MANIFESTATION IN MARITIME TRANSPORT

Context. There is a problem of identifying the subjective entropy of the navigator as an indication of negative human error in maritime transport. The aim of the study is to develop the data system to identify the negative manifestations of the human error for ensuring safety in maritime transport. Objective. The objective of the work is to design the data system consisting of two levels. Levels are targeted at detection of primary factors and secondary factors of subjective entropy of the navigator increase. Method. Within the scope of this work, the phases of the navigator’s activity are determined, in which negative manifestations of the human error arise. This most often occurs during emergency situations. It is determined that the navigator’s loss of focus leads to inadequate actions in relevant situations. Stressful situations are the second reason that affects self-control level. The factors’ expanses influencing the navigator’s subjective entropy increase as well as the vector affecting the subjective entropy at the first level of the formal system are determined. The arrangement of sets of factors was carried out. The arrangement result represents the formal system’s first level description. Multi-objective optimization problem is vital for optimal solutions identification. The patterning’s target is error evaluation on finding a vector, which is an essential stage. The lower limit of the system identification level is determined. The formal description of actions at the second level of the system is carried out and vector is specified at this level. The dependences of second-level vectors’ impacts on navigator subjective entropy increase are specified with maximum accuracy. Time input estimation for system actuation allows us to determine three operating modes of the system. The input data for operating modes specification is indicated. The matrix-based framework algorithm of navigator’s behavior during emergency situations is given. Results. Formal approaches were confirmed by simulation patterning using the navigation simulator NTPRO 5000. The data obtained allowed to build an algorithm in navigator’s shaping of in various situations. Conclusions. The proposed formal approaches, patterns and algorithms will provide a basis for navigator’s behavior analysis during emergency situations. The search of the best practice of human error data mining based on real data and simulator training data can be the direction for future research. This will allow to determine the mathematical expectation of navigator’s behavior in emergency situations, as well as when performing operations with a low coefficient of experience.

UTILIZING MACHINE LEARNING ALGORITHMS TO PREDICT THE SEVERITY OF MAJOR DEPRESSIVE DISORDER

Health care area is rising immensely from last few decades. It creates large amount of records about patients, clinical sources, infection analysis, electronic patient records, curative trials etc. Huge size records are a key source which needs preprocessing and evaluation for information mining that assists backing for cost-savings and verdict constructing. When medical organizations apply data mining on their prevailing data, they can realize new, beneficial and possibly life-saving information. Heterogeneity of major depressive disorder (MDD) disease progression muddles medical management. It can pretense dares for clinicians concerning correct analysis and actual well-timed cure. These challenges have provoked the increase of many machine learning techniques to aid advance the controlling of this disease. Machine learning (ML) is an application of artificial intelligence (AI) that offers structures the capability to mechanically acquire and improve from experience minus being explicitly programmed. Far-reaching data mining practices utilizing machine learning procedures have potential in the study of big epidemiological datasets. The following proposed research illustrates the idea of machine learning algorithms to analyze the depression epidemiological datasets in terms of its severity. Here, mean value substitution is performed on the data to preprocess it and then multiclass classifier machine learning algorithms are practiced to know the severity of the depression among the people at an early stage so that proper and correct timely treatment can be provided which will result in cost saving and faster improvement of health conditions of patients.

Learning Analytics and the Academic Library: Professional Ethics Commitments at a Crossroads

In this paper, the authors address learning analytics and the ways academic libraries are beginning to participate in wider institutional learning analytics initiatives. Since there are moral issues associated with learning analytics, the authors consider how data mining practices run counter to ethical principles in the American Library Association’s “Code of Ethics.” Specifically, the authors address how learning analytics implicates professional commitments to promote intellectual freedom; protect patron privacy and confidentiality; and balance intellectual property interests between library users, their institution, and content creators and vendors. The authors recommend that librarians should embed their ethical positions in technological designs, practices, and governance mechanisms.

A Different Approach to the Meaning and Mining of Small Data

Big data is rage in data mining but is typically limited to only big businesses. Small data is generally thought of as a subset of big data. For example, Google holds trillions of records used for searching, but this is not useful in and of itself. When one searches something on Google, typically only ten to fifteen results are shown on the first page. In order for this to occur, Google has taken big data and produced small data. The true value is in the small data subsets. This idea, however, that small data is the subset of big data, is not the only definition of small data. Small businesses, that only produce small data, can also benefit from data mining practices. What issues arise when only looking at small data?

Contexts, critiques, and consequences: A discussion about educational data mining and learning analytics

ABSTRACTThe capture, aggregation, and analysis of student data is becoming ubiquitous at all levels of education—from primary to post‐secondary—as institutions increase their adoption of information technologies to serve administrative and educational ends. In part, this has led to a growing interest among education scientists and administrators in strategically mining and analyzing troves of data in order to uncover student behaviors and intervene in student life. As is the case in other contexts where actors are pursuing Big Data's supposed benefits, educational data mining is fraught with moral, ethical, and political conflict. The panel is composed of four researchers who analyze and critique educational data mining practices and learning analytics initiatives in particular micro‐and macro‐contexts, including academic libraries and professional advising, urban schools, graduate‐level online learning, and higher education generally. Each panelist also represents a unique conceptual background, pulling from work in information ethics and policy, critical data studies, documentation studies, and higher education policy to empirically analyze and critically evaluate tools, systems, practices, policies, and values. Through their individual but thematically intertwined perspectives, the panelists will present their research and lead audience members in discussion.

Identifying restaurant satisfiers and dissatisfiers: Suggestions from online reviews

ABSTRACTAnalyzing data from user-generated websites with data mining practices can suggest meaningful insights into services performances. Such techniques may help identifying the precursors of service satisfiers and dis-satisfiers of restaurants. The aim of this research is to analyze online customer reviews for restaurants and underpin the restaurant satisfiers and nature of online restaurant reviews. After retrieving 2214 usable customer comments on Yelp.com, using a coded web spider, a series of both qualitative (e.g., tag clouds, word networks, and word trees were created using data visualization techniques) and quantitative (e.g., MANOVA) data analysis techniques were deployed to detect the satisfiers and dis-satisfiers of different types of restaurants. Three distinct types of clues – functional, mechanic, and humanic –explain a customer’s overall perception of a dining experience that lead to satisfaction or dissatisfaction. A focus on food, menu offerings, ambiance, and service create buzz in social media. Furthermore, several implications inform customer researchers about effective ways to investigate and serve the restaurant industry.

Performance forecasting for polymer flooding in heavy oil reservoirs

As a supply for future fuel and energy demand, 95% of the bitumen deposits in North America are expected to become a major source. The Steam Assisted Gravity Drainage (SAGD) provides more efficient recovery of unconventional oil resources, such as heavy oil and bitumen, as compared to the other thermal recovery methods. The drawback associated with SAGD or other thermal methods is that they are economically non-profitable when applied to the deep and thin reservoirs. Environmental concerns related to land, water, and air also hinder the application of the aforementioned methods. These issues have provoked reservoir engineers to employ a remarkable alternate such as polymer flooding recovery technique in heavy oil reservoirs. Quick and practical decision-making process in presence of uncertainty-based reservoir development scenarios is a notable stimuli for reservoir management teams to find substitute modeling techniques for future performance forecasting of heavy oil reservoirs. Cognitive data-driven analytics, including artificial and computational intelligence techniques, statistical analyses, and data-mining practices, offers an attractive alternate especially in presence of high-dimensional data space and predictive modeling of an extremely nonlinear system. This study utilizes an extensive data set from the half-century review of laboratory to field scales polymer flooding in heavy oil reservoirs provided by Saboorian-Jooybari et al. (2015) and (2016). The exploratory data analysis is implemented to construct a comprehensive training data set from polymer flooding experimental and field data, which involves various attributes describing characteristics associated with reservoir heterogeneities and pertinent operating parameters. Demonstrated results imply that this advanced data-driven modeling technique has a great potential to be integrated into all reservoir development tools for future performance predictions of the underlying processes.

Search, Mining, and Their Applications on Mobile Devices

In recent years, mobile devices have become the most popular interface for users to retrieve and access information: recent reports show that users spend significantly more time and issue more search queries on mobile devices than on desktops in the United States. 1 The accelerated growth of mobile usage brings unique opportunities to the information retrieval and data mining research communities. Mobile devices capture rich contextual and personal signals that can be leveraged to accurately predict users’ intent for serving more relevant content and can even proactively provide novel zero-query recommendations. Apple Siri, Google Now, and Microsoft Cortana are recent examples of such emerging systems. Furthermore, mobile devices constantly generate a huge amount of sensor footprints (e.g., GPS, motion sensors) and user activity data (e.g., used apps) that are often missing from their desktop counterparts. These new sources of implicit and explicit user feedback are valuable for discovering actionable knowledge, and designing better systems that serve each individual the right content at the right time and location. In addition, by aggregating mobile interactions across individuals, one can infer interesting conclusions beyond search and recommendation. Generating real-time traffic estimates is one example of such applications. This special issue focuses on research problems of search, mining, and their applications in mobile devices. Topics of interest in this special issue include but are not limited to mobile data mining and management, mobile search, personalization and recommendation, mobile user interfaces and human-computer interaction, and new applications in the mobile environment. The aim of this special issue is to bring together top experts across multiple disciplines, including information retrieval, data mining, mobile computing, and cyberphysical systems, such that academic and industrial researchers can exchange ideas and share the latest developments on the state of the art and practice of mobile search and mobile data mining.

Data mining of biometric data: revisiting the concept of private life?

Over recent years, a whole new process known as data mining, equivalent to automated techniques processing large sets of data in order to extract patterns, relationships, trends and other information not traceable through usual ‘human’ reading, has been largely gaining in repute. By taking advantage of the seemingly indefinite opportunities enabled by applications of data mining techniques, various fields of scientific or medical research, business transactions, state-related and other security-concerned activities, could gain unprecedented benefits. However, notwithstanding established data protection principles reserved also for biometric information, data mining practices, inherently intrusive in the private sphere of individuals, have generated various concerns and controversy. As these emerging technological developments create new challenges to the protection of personal data, including primarily the most sensitive category of biometric data, the effectiveness of the concept of privacy under the European Convention on Human Rights (ECHR) and of the existing EU data protection legislation in securing an adequate legal framework is facing a new ordeal. This paper seeks to review, especially in the aftermath of the recent Luxembourg Court’s case law, whether evolving data mining practices materialize the need of adjusting the legal treatment of biometric data protection.

Critical news reading with Twitter? Exploring data-mining practices and their impact on societal discourse

AbstractThis article shows that the collaboration between social science and computer science scholars proves fruitful in enhancing conceptual and methodological innovation in research appropriate for the digital world. It presents arguments for ways in which a multi-disciplinary approach can strengthen media studies and nnovatively advance both research breadth and depth. To illustrate this interesting connection of both disciplines, we present the example analysis of large data from Twitter and discuss this analysis in a communication science research environment. We propose TwiNeR, a software tool that analyzes tweet content using an advanced language modeling approach for classifying tweets into five prototypical messages referring to ‘activities’ related to news and news sources in the Twitter network (i.e., source-fed article, user-fed article, content spread by user, other source content, other user content).