Towards Mining Creative Thinking Patterns from Educational Data Nasrin Shabania aMacquarie University Sydney Australia

2025-04-26 0 0 7.33MB 51 页 10玖币

侵权投诉

Towards Mining Creative Thinking Patterns from Educational Data

Nasrin Shabani*a

aMacquarie University, Sydney, Australia

nasrin.shabani@mq.edu.au

ABSTRACT

Creativity, i.e., the process of generating and developing fresh and original ideas or products that are useful or ef-

fective, is a valuable skill in a variety of domains. Creativity is called an essential 21st-century skill that should be

taught in schools. The use of educational technology to promote creativity is an active study ﬁeld, as evidenced by

several studies linking creativity in the classroom to beneﬁcial learning outcomes. Despite the burgeoning body of

research on adaptive technology for education, mining creative thinking patterns from educational data remains

a challenging task. In this paper, to address this challenge, we put the ﬁrst step towards formalizing educational

knowledge by constructing a domain-speciﬁc Knowledge Base to identify essential concepts, facts, and assumptions

in identifying creative patterns. We then introduce a pipeline to contextualize the raw educational data, such as

assessments and class activities. Finally, we present a rule-based approach to learning from the Knowledge Base,

and facilitate mining creative thinking patterns from contextualized data and knowledge. We evaluate our ap-

proach with real-world datasets and highlight how the proposed pipeline can help instructors understand creative

thinking patterns from students’ activities and assessment tasks.

KEYWORDS

Educational Data Mining, Creativity Patterns, Data Curation

1 INTRODUCTION

In this section, we ﬁrst begin with an overview of the work and explain the problem statement which is under-

standing and identifying creative thinking patterns from raw educational data. Next, we provide our contributions

and explain how the proposed method greatly facilitates the process of discovering creativity patterns. Finally, we

outline the organization of this paper.

1.1 Overview and Problem Statement

Around the world today, original and creative ideas are the best and most important products of any powerful

country. This clearly shows the importance of recognizing and nurturing creativity in children from a young age.

Creativity is a set of skills that all humans have the capacity to possess, but it must be nurtured and expanded

under the right circumstances. Unlike earlier theories that assumed creativity as an inherited and intrinsic process,

recent research on creativity via education reveals that creative thinking, i.e., the ability to consider something in

a new way, is considered a skill and can be learned by individuals. Therefore, in countries with a dynamic educa-

tion system, fostering creativity has been considered one of the most important goals of education158.

Creativity is deﬁned in many diﬀerent ways, but almost all researchers and psychologists consent to a deﬁnition

that describes it as a process of generating ideas or products that are both unique and useful10. It may involve a

set of challenges, such as generating various solutions in response to a problem, spotting problems in the existing

state of knowledge, dealing with ambiguous circumstances, and bringing ideas into action. Hence, in the process of

creative pursuits, students need ongoing guidance, and training. But before providing personalized training, it is

needed to ﬁrst detect creativity patterns in students125.

arXiv:2210.06118v1 [cs.IR] 12 Oct 2022

There are numerous existing tools and techniques for measuring and detecting creativity such as divergent think-

ing tests174, self-report measures of creativity121, or judgment of products10 which have been traditionally used to

identify creative students. These approaches mostly involve evaluating the quality of ideas and products. Practi-

cally, using human evaluators to asses students’ responses to creative tasks, such as rating the uniqueness of ideas

from the alternate uses test, is a common element of doing creativity research. Although scoring systems have

proven eﬀective, they are susceptible to two fundamental limitations: labor cost and subjectivity, which pose spe-

ciﬁc psychometric risks to reliability and validity26.

Recent development in learning management systems has proved to assist diﬀerent educational assessments and

minimize the aforementioned limitations. These technologies have the capacity to gather and visualize large amount

of educational data, e.g., assessments and class activities. In this context, helping instructors to understand the ed-

ucational data remains a challenging task71. There is a large amount of work aiming to discover insight from edu-

cational data, with the goal to support traditional learning and educational assessments15, 57, 147, 149. However, the

current state of the art lacks a signiﬁcant data-driven strategy to link students’ behaviour to creativity patterns.

In this paper, to address these challenges, we construct a domain-speciﬁc Knowledge Base (KB) to identify essen-

tial concepts, facts, and assumptions in identifying creative patterns. We then introduce a pipeline to contextual-

ize the raw educational data, such as assessments and class activities. Finally, we present a rule-based approach

to learning from the Knowledge Base, and facilitate mining creative thinking patterns from contextualized data

and knowledge. We evaluate our approach with real-world datasets and highlight how the proposed framework can

help instructors understand creative thinking patterns from students’ activities and assessment tasks.

1.2 Contributions

In this study, we propose a rule-based insight discovery method to discover patterns of creativity in educational

data. Our work relies on the knowledge of experts in education for buildings a domain speciﬁc Knowledge Base to

be linked to the extracted features from educational data. To achieve this goal, we ﬁrst imitate the knowledge of

domain experts into an Educational Knowledge Base, i.e., a set of concepts organized into a taxonomy, instances

for each concept, and relationships among them. Secondly, to drive insight from raw data we propose a method to

link the concept nodes in the taxonomy to the entities extracted from educational data.

Our approach is based on a motivating scenario in educational assessment, where a knowledge worker (e.g., a teacher)

may need to analyze the activities of students in a classroom and augment that information with the knowledge in

the educational Knowledge Base. Making beneﬁt from a user-guided rule-based technique the person can link the

information extracted from raw educational data to creativity patterns, identiﬁed in the educational Knowledge

Base.

The unique contributions of this paper are:

•We put the ﬁrst step towards formalizing the educational knowledge by constructing a domain-speciﬁc Knowl-

edge Base to identify essential concepts, facts, and assumptions in identifying creative patterns.

•We introduce a pipeline to contextualize the raw educational data, such as assessments and class activities.

We customize existing data curation techniques to turn the raw educational data into contextualized data

and knowledge.

•we present a rule-based approach to learn from the Knowledge Base, and facilitate mining creative thinking

patterns from contextualized data and knowledge.

•We evaluate our approach with real-world datasets and highlight how the proposed framework can help in-

structors understand creative thinking patterns from students’ activities and assessment tasks.

1.3 Summary and Outline

In this section, we gave a broad picture of the problem and covered the motivation, problem statement, and contri-

butions of this paper. The remaining of this paper is structured in the following manner:

•In Section 2 we will present the background and analyze the related work in the education domain. We will

review the current state-of-the-art approaches, including educational knowledge, educational modelling, Open

Learner Models, and Educational Data Mining techniques. We will provide a summary to compare the re-

viewed methods and techniques in the four areas.

•In Section 3 we will explain our methodology towards mining creative thinking patterns from educational

data. This section will provide detailed information about the proposed method which includes building an

Educational Knowledge Base, data curation, feature selection, building a Knowledge Graph, and ﬁnally link-

ing the graph to the proposed knowledge base using a novel rule-based technique.

•In Section 4 we will present the experiment, results, and evaluation. We will discuss a motivating scenario

to clarify our approach to the reader and then explain the experiment’s dataset and setup. We will conclude

this section with a discussion over the evaluation results.

•Finally, in section 5, we will conclude the study by providing a summary of the proposed method. We will

also discuss the future directions that we build on our study.

2 BACKGROUND AND STATE-OF-THE-ART

In this section, we study and analyze the recent work in modelling and mining educational data. We introduce the

key terms and background in the ﬁeld, and then discuss the related works in Educational Data, Educational Data

Modeling, Open Learner Models, Educational Data Mining, and Learning Analytics. We conclude the section by

summarizing the challenges in educational data mining and analytics, and highlight the added value of our pro-

posed approach.

2.1 Data in Education

2.1.1 Data, Metadata, and Big Data

Data in computing refers to the information that is converted to a digital format that could be stored and pro-

cessed. Individuals, machines, and sensors, as sources of information, are generating a massive amount of data

each second. For example, individuals generate data when they take a photo using their digital devices, browse

the internet, or publish content on their social media. Smart devices such as cars, watches, TVs, and phones also

sense and create data even when they are not in use30, 154.

Data can be stored in three formats: structured, unstructured, and semi-structured. Structured data consists of

data types that are well deﬁned and have patterns that make them easy to search including student name, ID

number, and age. Unstructured data consists of data types that are often diﬃcult to search, including text, pdf,

image, and video. And, semi-structured data consists of a loosely organized meta-level structure that can contain

unstructured data, e.g., Email, HTML, XML, and JSON documents. From the processing point of view, data pro-

cessing consists of organizing, curating, analyzing, and presenting operations29.

Metadata refers to as the information that describes other data. It is also deﬁned as a preﬁx that provides an ’un-

derlying deﬁnition or description’ in most information technology applications181. Metadata describes fundamental

data information, making it simpler to discover, utilize, and reuse speciﬁc data instances. For example, a docu-

ment ﬁle’s metadata includes the creator’s information, the date that has been created or updated, and the ﬁle for-

mat. In addition, metadata can be used for relational databases, images, videos, audio ﬁles, and web pages. By us-

ing the tracking method, smart devices such as phones or watches track our location, speed, the Apps and gadgets

we are using, and the music we often listen to. Or, smart TVs can track the channels we watch, time and dura-

tion, and the Apps we use during a speciﬁc time of day41. Metadata oﬀers a primary description of an information

item, and it should be appropriately speciﬁed in terms of granularity, structure, quality, and provenance5, 37, 39.

Big Data refers to a set of large datasets that are so vast, fast, or complicated. Processing such data using stan-

dard methods could be diﬃcult or impossible. The term also refers to the technology that is used to manage the

generated data and metadata. The everyday exchanged data on the Internet, social media contents and feeds, and

mobile phone location data are examples of big data. Construction, healthcare, insurance, telecommunications,

and ecommerce are among the areas where big data is becoming increasingly important.

Wide data dispersion, a variety of formats, non-standard data models, and heterogeneous semantics are all charac-

teristics of big data. It should be notes that several challenges are involved while using big data such as the way it

should be organized, curated, analyzed, and visualized30.

Big data is characterized by the following attributes (also known as four Vs196): Volume (size of data), Velocity

(speed of data streaming), Variety (data types), and Veracity (uncertainty of data).

•Volume: The volume of data is the deﬁning attribute of big data. Individuals, machines, and organizations

create data from numerous sources, from which reliable information is collected and integrated at the organi-

zation center. For example, consider the wide range of data collected from students using their smart phones,

evaluations, homework, feedback forms, surveys, etc. This mass of data creates a huge amount of data that

must be appropriately analyzed.

•Velocity: This attribute of big data gives an indication of data speed, or the rate at which data is emerging

from diverse sources. This high speed data is enormous and arrives in a constant stream, necessitating fast

processing.

•Variety: The data that is received for processing might take many diﬀerent ﬁle forms from structured to

unstructured data. Formats such as ‘.XLS’ or ‘.XLSX’ (Excel ﬁle), ‘.CSV’ (comma-separated values ﬁle),

‘.TXT’ (plain text ﬁle), ‘.PDF’ (PDF ﬁle), or ‘.RTF’ (rich text ﬁle). Data can arrive in a variety of formats,

including audio, image, video, SMS, maps, geographical data or something we hadn’t considered. It is criti-

cal for organizations to eﬀectively handle such a diverse set of data, as there is currently a broad selection of

data formats from which to extract information.

•Veracity: There are several data stream sources accessible, each of which creates a signiﬁcant amount of

data. Due to the large number of sources accessible, this data is susceptible to outliers or noise. As a result,

the data’s nature or behavior may change. Veracity deals with the uncertainty of data, which has a signiﬁ-

cant inﬂuence on the organization’s decision-making process.

Recently, the four Vs concept has been expanded into numerous Vs. For example, big data is classiﬁed into ﬁve

Vs (Volume, Velocity, Veracity, and Value) in one research69, while characterized into seven Vs in another one by

adding two other new concepts such as Valence, and Variability152.

2.1.2 Educational Data

A wide range of educational data is accessible from a number of diﬀerent sources. By using the educational data

teachers may now monitor their students’ academic achievements, learning behaviors, and oﬀer immediate feed-

back based on the needs and requirements of students. Learning management systems collect a huge quantity of

data from students that may be used to improve the learning environment, assist teacher in teaching and students

in learning, and enhance the learning experience in general. Diﬀerent learning resources are available which a num-

ber of them can be listed as follows21:

•Interaction between students, instructors, and also students and instructors (e.g., chat boxes, discussion fo-

rums, navigation behavior).

•Administrative data (e.g., institution, courses, instructors),

•Demographic data (e.g., age, nationality, gender),

•Students’ activities (e.g., assessments, questions, feedbacks),

•Students’ dispositions and aﬀectivity (e.g., attitude and motivation).

Since traditional learning analytics are not equipped to handle this volume of data, big data technologies and tools

have found their way into education to process this massive amount of data. To deal with diﬀerent kinds of educa-

tional challenges administrative data could be very useful. As a result, experts should acknowledge the inﬂuence of

big data in education in order to alleviate educational diﬃculties.

In the big educational data, several research and review studies have been conducted. Highly cited studies investi-

gated themes14 such as: (i) Behaviour and performance of learners: Dedicated to learner perspectives, fulﬁllment,

methods, and behaviour, as well as big data structures, adaptive learning, teaching, data mining, and learning ana-

lytics59, 61; (ii) Educational data modeling and warehouse: Introducing big data modeling, educational data ware-

houses, and cloud environment research, as well as cluster analysis for educational purposes137, 194; (iii) Improving

educational system: Introducing statistical tools, metrics, obstacles, and the usefulness of ICT. It places a strong

emphasis on training and its numerous ramiﬁcations. It also establishes a rating system that monitors how web-

sites are used in order to enhance the educational system117, 130; and (iv) Merging pedagogy with big data: Incor-

porating big data concepts into various courses and emphasizing their educational implications52, 73.

2.1.3 Educational Environments

The environment in which a student gets educational services is referred to as the educational environment. There

are three types of educational environments available for diﬀerent users such as face-to-face learning, E-learning,

and blended learning182.

•Face-to-face learning refers to educational methods in which instructors and students meet in a certain loca-

tion at a speciﬁc time for one-by-one or group class sessions, similar to what occurs in schools.

•E-learning involves any and all information delivery using digital technology for teaching and learning in

education. E-learning became the foundation of modern education due to the progress of technology in in-

formation and communication. Individuals can beneﬁt from the environment without the time and space

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

TowardsMiningCreativeThinkingPatternsfromEducationalDataNasrinShabani*aaMacquarieUniversity,Sydney,Australianasrin.shabani@mq.edu.auABSTRACTCreativity,i.e.,theprocessofgeneratinganddevelopingfreshandoriginalideasorproductsthatareusefuloref-fective,isavaluableskillinavarietyofdomains.Creativityiscall...

展开>> 收起<<

Towards Mining Creative Thinking Patterns from Educational Data Nasrin Shabania aMacquarie University Sydney Australia.pdf

共51页,预览5页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

Towards Mining Creative Thinking Patterns from Educational Data Nasrin Shabania aMacquarie University Sydney Australia

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: