No abstract

Geographic information system (GIS) is designed to generate maps, manage spatial datasets, perform sophisticated “what if” spatial analyses, visualize multiple spatial datasets simultaneously, and solve location-based queries. The impact of big data is in every industry, including the GIS. The location-based big data also known as big spatial data has significant implications as it forces the industry to contemplate how to acquire and leverage spatial information. In this study, a comprehensive taxonomy is created to provide a better understanding of the uses of GIS and big spatial data. The taxonomy is made up of big data technologies, GIS data sources, tools, analytics, and applications. The authors look into the importance of big spatial data and its implications, review the data sources, and GIS analytics, applications, and GIS tools. Furthermore, in order to guide researchers interested in GIS, the challenges that require substantial research efforts are taken into account. Lastly, open issues in GIS that require further observation are summarized.

The phenomenon of fake news has become a much contentious issue recently. The controversy regarding this issue has further been intensified by the openness of social media platforms. Via a systematic review, this paper offers a discussion on the spread and detection techniques of fake news on Social Networking Sites (SNSs). A total of 47 articles eventually fulfilled the inclusion criteria and were coded for the literature synthesis. The overall findings from the literature on fake news and social media have been extracted and synthesized to explore the creation, influence and popular techniques and dimensions used for fake news detection on SNSs. The results showed that various entities are involved in the creation and spread of fake news on SNSs, including malicious social and software agents. It was also found that early registered users, old people, female users, delusion-prone persons, dogmatic persons, and religious fundamentalists are more likely to believe in fake news than other groups of individuals. One of the major problems of the existing techniques is their deficiency in datasets. Therefore, future studies on fake news detection should focus on developing an all-inclusive model with comprehensive datasets. Social media users require fake news detection skills especially using linguistic approach. This study provides the public with valuable information about the spread and detection of fake news on SNSs. This is because SNSs are an important avenue for fake news providers.

<span>Feature engineering (FE) is one of the most important steps in data science research. FE provides useful features to be used later in the study. Due to climate change, the research focus is moving towards air quality estimation and the impacts of air pollution on health in Malaysia. Malaysia has 66 air quality monitoring (AQM) stations, and the air quality data for research is provided in an excel worksheet format by the Department of Environment, Malaysia. The data generated by the AQM stations is in a raw custom format, and it is virtually impossible to clean and engineer this data manually due to the sheer number of files. Hence, we propose a novel feature engineering algorithm to transform and combine this data into a useable format. The results show that the proposed feature engineering algorithm was able to efficiently extract and combine the hourly and daily values for pollutant and meteorological variables in useful row format. This algorithm will help all the researchers using the data from the AQM station in Malaysia as well as other countries using the same AQM station. The implementation of the feature engineering algorithm is also available to use at GitHub (https://github.com/rajasherafgun/featureengineeringaq) under AFL-3.0 license.</span>

<p>Learning Management System (LMS) is an online software that was hosted on a server and designed specifically to manage learners’ information, course registration, learning content, and assessment tool. Educational data mining is a way of evaluating and using methods for examining the unique and large dataset that come from educational field, and applying those in order to understand how students learn and the settings in which they learn. Many students use to miss some of the activities posted by their instructors, due to the short deadline, and they are not accessing the LMS regularly or every day. The purpose of this paper is to explore the way on how student access LMS and which day is the most frequent accessed. The findings show that, the total number of accessing LMS among 33 students is 16060, and the mean is 486.67, S16 recorded the highest number of accessing the LMS (965 access), while S24 as the least number of access (275). And the correlation between Tuesdays is significant, positive and strong correlation with Wednesdays (0.546), and positive, but weak with Thursdays (0.292), Fridays (0.244), Saturdays (0.334), and Sundays (0.291).</p>