Sequencing Wikipedia Pages: An On-the-ﬂy Approach to Course

Building

Fabio Gasparetti, Carla Limongelli, Alessandra Milita, Filippo Sciarrone and Andrea Tarantini

Department of Engineering, Roma Tre University, Via della Vasca Navale 79, Rome, Italy

Keywords:

E-learning, Sequencing, Wikipedia.

Abstract:

With its 5, 006, 202 articles, 49 millions of registered people and on average 800 new articles per day,

Wikipedia provides a knowledge base for teachers and instructional designers to build didactic materials.

As a matter of fact, teachers often consult this encyclopaedia to arrange, integrate or enrich their courses.

Moreover, with the exponential growth of the Internet, didactic materials are freely available and usable by

teachers, instructional designers and students from Learning Objects Repositories such as Mertlot or Ariadne

and others. On the other hand, designing and delivering a new course is a crucial task for teachers, who have

to face two main problems: building or retrieving and sequencing learning materials. Retrieving or building

learning materials requires a great effort and is time-consuming, while sequencing requires an accurate didac-

tic project. In this paper we present a sequencing engine of learning materials, embedded in the Wiki Course

Builder system, a system capable of retrieving and sequencing Wikipedia web pages, taking into account both

the teacher model based on the Grasha teaching styles and on a social didactic approach. The main goal is

to support teachers building on-the-ﬂy courses, i.e., building courses quickly, with a few clicks of the mouse.

An important feature of the system is represented by its ability to allow teachers to interact with the recom-

mended learning path through a graph-based interface where they can directly modify the proposed learning

path, adding or deleting Wikipedia pages. A ﬁrst questionnaire has been submitted to a sample of teachers

with encouraging results.

1 INTRODUCTION

Nowadays, the Internet can be considered a big repos-

itory of didactic materials, strengthening the lifelong

learning era. Wikipedia

with its 5, 006, 202 articles,

49 millions of registered people and on average 800

new articles per day has become one of the most vis-

ited didactic repositories, due to its simplicity of use

and to its knowledge base, freely put on line by a

huge and free community of experts such as teachers,

instructional designers, scientists, and so on. Also,

most people use Wikipedia as a readily available di-

dactic material repository, quick and simple to con-

sult (it does not require a registration process). On

the other hand, if the use of Wikipedia in Education is

still very controversial and Wikipedia contents are not

always considered scientiﬁc contributions to be ac-

cepted in school, some learning experiences state that

about 87%,

use the online Wikipedia Encyclopedia

www.wikipedia.org

www.pewinternet.org/2013/02/28/how-teachers-are-

using-technology-at-home-and-in-their-classrooms/

in their didactic activities. Furthermore, the reliabil-

ity of Wikipedia, primarily of the English-language

edition, has been also assessed: an early study in the

journal Nature said that in 2005, Wikipedia’s scien-

tiﬁc articles came close to the level of accuracy of the

Encyclopedia Britannica.

In this paper, we propose a system, called Wiki

Course Builder, (WCB) that helps teachers to retrieve

and sequence Wikipedia HTML pages taking into ac-

count both the model of the particular teacher that

launched the query and the hypertext structure of the

Wikipedia pages. The WCB system was ﬁrst intro-

duced in a previous work (Gasparetti et al., 2015c),

mainly focussing on the retrieving capabilities of rel-

evant Wikipedia pages, while here we address the

sequencing engine module. This repository forms

a huge semantic graph of relevant contents and we

chose it as the system content source for its popular-

ity among students, instructional designers and teach-

ers. Moreover, people regularly use it as the starting

point for knowledge building and for identifying gen-

eral didactic goals, especially in a lifelong learning

Gasparetti, F., Limongelli, C., Milita, A., Sciarrone, F. and Tarantini, A.

Sequencing Wikipedia Pages: An On-the-ﬂy Approach to Course Building.

In Proceedings of the 8th International Conference on Computer Supported Education (CSEDU 2016) - Volume 1, pages 397-404

ISBN: 978-989-758-179-3

397

context. In our system, through a suitable GUI, the

user can input one or more keywords concerning the

topic he/she is working on. Subsequently, the sys-

tem analyzes the most relevant Wikipedia pages, re-

turned by the embedded search engine, together with

a proposal of a ﬁrst sequencing of them. Both the

retrieving and sequencing engines are based on the

Grasha Teaching Styles Model (Grasha, 1996), a sim-

ple teaching model based on ﬁve dimensions of teach-

ing. Each teacher registered into the WCB system

is ﬁrstly required to take a simple standard question-

naire, the Grasha-Riechmann Teaching Style Survey,

available at http://longleaf.net/teachingstyle.html and

directly linked from the WCB system, receiving in

output her teacher model. Besides, in the retrieving

process, the relevance of a Wikipedia page is related

to the set of the teaching styles tags associated to it: a

Wikipedia page used by a teacher is tagged with her

model (ﬁve dimensions). Subsequently, the sequenc-

ing is proposed by the system, basing on the links

among the retrieved pages, on the Grasha teaching

styles associated to each Wikipedia page already used

by the community and on the model of the teacher

that is building the course. In fact, each time a teacher

inserts a retrieved document into her course, the doc-

ument itself is tagged with her teaching styles, rep-

resented by an array of ﬁve real numbers, represent-

ing the Grasha model. As time goes by, this form of

knowledge is acquired and exploited so that the repos-

itory content is automatically ﬁltered. In fact, each

Wikipedia page tagged by different users is weighed

with the average of all the ﬁve dimensions of all the

teachers that used it in a course. The well-known cold

start problem of collaborative approaches is partially

overcome by exploiting the ﬁrst visits of the resources

as soon as they become available. This is a straight-

forward and lightweight approach, well suited for a

Community of Practice (CoP) (Wenger, 1998), where

multiple users access and ﬁlter Wikipedia pages, with

the common goal to quickly build a new course. The

remainder of the article is structured as follows. Sec-

tion 2 draws some important related work. Section 3

shows the teacher model the sequence engine is built

on. Section 4 shows the system, i.e., the WBC system

while Section 5 focuses on the sequencing engine. In

Section 6 a ﬁrst evaluation of the system is presented.

Finally in Section 7 some conclusions are drawn.

2 RELATED WORK

Our proposal aims to sequence Wikipedia web pages

basing on the teacher model, as deﬁned by Grasha in

(Grasha, 1996). So, Wikipedia, Grasha model and se-

quencing techniques represent the key concepts that

set up our system.

To our knowledge, there is not much literature

that considers the possibility to retrieve and sequence

Wikipedia pages to build a new course, while there is

some literature concerning the retrieval and sequenc-

ing of didactic material on the basis of the Grasha

teacher model. The use of the Grasha model can be

found in (Limongelli et al., 2015; Limongelli et al.,

2016), where the teacher model is represented by a

teaching experience and a dynamic semantic network

composed by the retrieved and used learning materi-

als by a community of teachers. In (Limongelli et al.,

2013b) a clustering of teachers is proposed for a com-

munity of teachers.

One of the ﬁrst works which have investigated

Wikipedia as a learning support is (Forte and Bruck-

man, 2006). In particular, this work addresses the

following research question: Publishing on Wikipedia

encourages students towards a collaborative and in-

volving learning?. Then, (Parker and Chao, 2007)

highlights the didactic potential of wikis that actively

involve learners in their own construction of knowl-

edge, on the basis of a collaborative approach. Gas-

paretti et al. (Gasparetti et al., 2015b; Gasparetti

et al., 2015a) propose an early attempt to exploit the

Wikipedia content in order to determine prerequisite

relationships among learning objects.

However, sequencing methods and techniques

have been widely investigated. Generally, course Se-

quencing techniques can be classiﬁed in the following

two main categories (Limongelli et al., 2009; Sciar-

rone, 2013):

• Sequencing that plans the entire learning path at

the beginning of a course, modifying it if the

study should not succeed as it should; e.g., Dy-

namic Courseware Generation (Brusilovsky and

Vassileva, 2003), the work of Baldoni et al. (Bal-

doni et al., 2007)(Baldoni et al., 2004), and the

IWT system (Sangineto et al., 2008; Limongelli

et al., 2013a; Sterbini and Temperini, 2013);

• Sequencing obtained in an implicit way, step by

step, through adaptive navigation support tech-

niques, such as adaptive link annotation and di-

rect guidance (Brusilowsky, 2001; De Bra et al.,

2006; Limongelli et al., 2012a; Limongelli et al.,

2012b).

All the aforesaid proposals take into account the stu-

dent model required to build an adaptive sequencing

engine. Our system does not take into account the

student model but proposes the learning path on the

basis of the teacher model only. Another important

characteristic of our system is the use of Wikipedia as

the source of didactic material. Wikipedia has been

CSEDU 2016 - 8th International Conference on Computer Supported Education

398

used as a didactic source in many attempts to extract

useful information about the relevance of its contents.

In particular, in (Milne and Witten, 2013) an inter-

esting toolkit is presented to manage the Wikipedia

contents by a semantic point of view. In (Strube

and Ponzetto, 2006) a comparison between Wikipedia

and WordNet is presented in the WikiRelate! sys-

tem, to ﬁnd semantic relationships among terms. In

(Gabrilovich and Markovitch, 2009) a Wikipedia-

based semantic interpretation for natural language

processing is presented. A novel method, called Ex-

plicit Semantic Analysis, for ﬁne-grained semantic

interpretation of unrestricted natural language texts,

is presented. This method represents meaning in

a high-dimensional space of concepts derived from

Wikipedia, representing the meaning of any text in

terms of Wikipedia-based concepts. Another work

worth of mention is that of Turchi et al. (Turchi

et al., 2015) where the MediaWiki search engine,

made available by Wikimedia Foundation to search

contents among Wikipedia web pages, is used to test

a ranking algorithm based on Swarm Intelligence.

In conclusion, the characteristics of our approach

to the sequencing problem merges two research ﬁelds,

the use of Wikipedia and the use of a teacher model.

Both approaches have been used separately and in dif-

ferent contexts so far, while our proposal uses them

synergistically.

3 THE TEACHER MODEL

The teacher model is a crucial element of our proposal

because the sequencing engine is based on it and acts

accordingly. The model building process starts with

the Login module, by which the user can register and

join the community of teachers. A database of users

is built and managed by this module. When the user

registers into the system, she is required to ﬁll in a

form with some personal data. It is in this step that the

user is required to take the Grasha-Riechmann Teach-

ing Style Survey

. It consists of a set of 40 5-points

Likert-scale questions, such as: Sharing my knowl-

edge and expertise with students is very important to

me and I give students negative feedback when their

performance is unsatisfactory. The questions aim at

modeling the teacher by means of the following ﬁve

dimensions:

• Expert: the teacher has the knowledge and the ex-

perience that students need;

• Formal authority: the teacher maintains her/his

institutional role;

available at: http://longleaf.net/teachingstyle.html

• Personal model: the teacher bases her/his teach-

ing on personal examples and establishes a model

for thinking and acting;

• Facilitator: the teacher emphasizes personal in-

teractions between students and teacher;

• Delegator: the teacher develops the students abil-

ity so that they can act autonomously.

where each dimension is measured by a real number

d ∈ [1, 5]. In this way, when the user registers into

the system, she is modelled by the set of the aforesaid

ﬁve dimensions. Subsequently, this data will be used

by the search engine. Fig. 1 shows an example of a

teacher model as computed by the Grasha-Riechmann

survey.

Figure 1: An example of teacher model: Expert=2.875,

Formalauthorithy=3.625, Personalmodel=2.875, Facilita-

tor=3.0, Delegator=1.625.

4 THE SYSTEM

In this Section, we show the general architecture of

the system. The WBC system acts as a recommender

system supporting teachers in building new courses,

taking contents from Wikipedia, through a very sim-

ple and, above all, fast process. The teacher has the

possibility to change, discard or review the recom-

mended web pages, changing the proposed learning

path as well.

4.1 The Architecture

The system is composed of some general functional

modules (Gasparetti et al., 2015c), as shown in Fig. 2.

Here we focus on the following subsets of modules

• The Login Manager Module. This module reg-

isters new users allowing them to enter into the

system. Subsequently, it proposes the Grasha-

Reichmann Survey by means the teachers can

build their own teaching model, as shown in Sec-

tion 3. Each teaching model is then stored in a

local repository, ready to be used in the retrieval

process;

http://blacky.dia.uniroma3.it:9080/login.html

Sequencing Wikipedia Pages: An On-the-ﬂy Approach to Course Building

399

• The Terms Manager Module. This module man-

ages the topic-terms and the context-terms in-

serted by the users during the query building pro-

cess. These sets of terms are then passed to the

search engine to retrieve relevant pages from the

Wikipedia repository. Moreover, these terms are

stored in the local repository, in order to display

them in a Google-like way, when building a new

query;

• The Page Manager Module. This module is com-

posed of two sub-modules: the My Courses and

the Build Course module. Through the ﬁrst mod-

ule the users can revise their courses, changing

the learning paths, export the courses, and so on.

The second module manages the sequencing en-

gine, allowing to build new courses. Worth of

mention is the capability of this module to display

the graph of the connections among the retrieved

Wikipidia pages. It helps teachers to have a sim-

ple and graphic interface to the recommended

learning path in order to modify it, by adding or

deleting learning nodes directly.

Manager

Users

Terms Manager

Engine

Context Terms

Wan

Wikipedia Pages

New

Course

Query

Terms

Wikipedia

HTML Pages

Filtering

Process

Sequencing

and Ranking

Pages

Manager

Teacher

Local Wikipedia Pages

Teacher

Wiki Course

Figure 2: The general architecture of the Wiki Course

Builder system.

5 THE SEQUENCING ENGINE

In this section we show the entire process of building

a learning path to insert in a new or old course. The

session starts with a teacher having the My Courses

repository empty. Subsequently, the teacher can cre-

ate a new course, as shown in Fig. 3 where a

new course, concerning the java programming lan-

guage topic, is to be created. Once inserted the

topic-terms and the context-terms, the system returns

those Wikipedia pages deemed relevant for the query.

In fact, the user, through a Google-like interface,

can specify the keywords in the ﬁrst input text ﬁeld

(the topic-terms) together with other terms, to disam-

biguate the context (the context-terms), in the second

text ﬁeld. The system keeps track of all the topic-

terms already inserted, with their related context-

terms. Finally, clicking the Submit button, the sys-

tem returns a group of Wikipedia pages, ranked on

the basis of the distance between the teaching model

of the teacher who launched the query and the teach-

ing styles of each retrieved page, computed as an Eu-

clidean distance metric D between the user teaching

styles TS

and the generic document TS

u,d

∑

i=1

(TS

− TS

)

(1)

The retrieved pages, displayed in a results-table,

can be ranked also by means of the cosine similar-

ity between the query and each Wikipedia retrieved

page, by means of a TFxIDF terms-weighting tech-

nique (see for example (Baeza-Yates and Ribeiro-

Neto, 1999)). The system uses the TFxIDF tech-

nique, which is not based on didactic features, only

at the time t

, that is when the retrieved pages are all

cold items. Every time the teacher uses a retrieved

page in a course, this page is tagged with her teaching

styles. In this way, by the use of the system, each used

Wikipedia page (i.e., a link to it) will be stored in a lo-

cal database together with a set of the 5-tuples of the

teachers who used it in their courses: if a teacher used

a page n-times, this page will be tagged n-times with

the user teaching styles. In this way, the system keeps

track of the choices made by the members of the com-

munity, strengthening the social aspects of the page

selection process. Obviously, in the Wikipedia repos-

itory, the topics do not have a uniform distribution in

terms of number of related pages: it may be that for

different topics there is a different number of related

pages stored in the Wikipedia database. In the case

of none of the Wikipedia pages should match the user

query, other topic-terms are required. Moreover, the

retrieval process could be more or less time consum-

ing, depending on the granularity of the query. From

the results table the user can perform the following

actions:

1. Clicking the title of each page, after that the sys-

tem proposes a new window showing the web

page directly from Wikipedia. In this way the

teacher can assess more accurately its content;

2. Changing the ranking algorithm: by Title, by

Teaching Styles or by cosine similarity;

3. Clicking the process button to launch the sequenc-

ing engine. In this case, the system processes all

the links belonging to that page and returns a se-

quence of three pages. Once the teacher has given

CSEDU 2016 - 8th International Conference on Computer Supported Education

400

Figure 3: The Course Building Process. The left screen-shot shows the starting form where teachers can insert their topic-

terms; the right screenshot shows the pages returned by the search engine for the java programming language query.

Figure 4: The sequencing process: the left screenshot shows the learning path returned by the system; the right screenshot

shows the ﬁnal learning path inserted into the new course (java programming language).

the new course a title and a description, by click-

ing on the Apply button, the new empty course is

added to the My Courses list of the courses owned

by her. In Fig. 4 the sequencing selection pro-

cess is shown. For each course, users can view

the details, change the title and/or description and

delete the course. To store the new course and to

make the changes effective it is then necessary to

click the save button at the top right of the screen.

Once created the course, the user can populate it

with didactic contents.

In particular, the sequencing engine parses the

Wikipedia page related to the process button, to iden-

tify its outbound links. For each linked Wikipedia

page, the system selects the more promising page,

including it in the recommended learning path. In

the case of ties, the system uses the cosine similarity

as it does in the previous phase of the search results

ranking. These operations of parsing, calculating the

Euclidean distance and selection of the most promis-

ing page are then repeated a ﬁnite and parameterized

number of times. Currently the system is set up to

compute three levels of depth, but the user can change

this parameter. The returned learning path is shown in

Fig. 4 where from the top of the list to the bottom a

learning path consisting of three pages, is displayed.

For each item of the results-set, the user can display

it, move it up or down, changing the ranked list and

delete it. After these operations, the learning path is

inserted into the new course.

5.1 The Sequencing Graph

Management

Another important feature of the system, is its capa-

bility to allow the user to visualize and to directly

interact with the graph of the course by means of a

graphical interface based on the Gephi graph man-

ager, an open source software to manage graphs

. The

system displays the graph formed by the learning path

together with all the Wikipedia linked pages. Click-

ing on the i icon, the user launches the graph envi-

ronment. In Fig. 5, highlighted in red, are shown

the three nodes forming the recommended learning

path. Clicking on a node, the system highlights all

the links and all the nodes directly connected with it,

www.gephi.org

Sequencing Wikipedia Pages: An On-the-ﬂy Approach to Course Building

401

both inbound and outbound, as shown in Fig. 6. On

the left of the graph the system shows a frame con-

taining some important characteristics of the selected

node: the name of the page together with its link to

Wikipedia, the distances computed both by teaching

styles and cosine similarity for that node, the URLs of

all the Wikipedia pages directly connected to it. By

clicking one of these URLs, the system opens a new

browser window displaying the selected page. In this

way, the teacher can verify the quality of the learning

path suggested by the sequencing engine checking for

other topics to add to the recommended learning se-

quence, as shown in Fig. 6. To add a node to the

learning path the user just selects it in the graph and

then clicks the link on the left Add this page to list.

The system opens a dialog box conﬁrming the inser-

tion. After having saved the course, each Wikipedia

page included in this course is tagged with the 5-tuple

of the teacher owner of the course. Moreover, when

using the same Wikipedia page in different courses,

this page is tagged with the Grasha 5-tuples of the

Figure 5: The graph with, in red color, the recommended

learning path for the java programming language course.

Figure 6: The user has clicked on the java node: the system

proposes the Programming Language node.

course owner once more. For each Wikipedia page

tagged by the system, the system stores its 5-tuples,

indicating the teaching styles of thepage and the num-

ber of contributions to its calculation. For example,

if three users are using the same Wikipedia page,

this page will be associated with the Grasha quintu-

ple [x

, x

], in which each element x

is com-

puted as the arithmetic mean of all the values of the

three teaching styles of the users who have used it

in their courses. Moreover, the system associates to

each used page an incremental counter keeping track

of how many users have used the page. The presence

of the counter allows to obtain weighted values for the

calculation of the new tags. If a user decides to delete

a page from its course, the counter is consequently

updated. Finally, at any time the user can return to the

My Courses section to view the details of her course

with the possibility to edit or delete it.

6 A FIRST EVALUATION OF THE

SEQUENCING MODULE

In this Section we show a ﬁrst evaluation of the

sequencing engine. We submitted a happy sheet

questionnaire, composed of 5 questions, to a sample

formed by 10 teachers teaching in a technical high

school with the aim to test the feeling of teachers with

respect to the sequencing process. The sample was re-

quired to create a new course on a Computer Science

topic. The following ten courses were built: mother-

board, java language, array, microprocessor, switch,

router, c language, Von Neumann, Turing and Uniﬁed

Modeling Language. A question was about the use-

fulness of the recommended sequencing: Did you ﬁnd

useful the sequencing proposed by the system?. An-

other question was: How do you feel the GUI of the

sequencing module?. The answers to the ﬁrst ques-

tion are shown in Fig. 7. 70% of the sample con-

sidered the system useful and very useful. In Fig. 8,

Figure 7: Do you ﬁnd useful the sequencing proposed by

the system?

CSEDU 2016 - 8th International Conference on Computer Supported Education

402

are summarized the answers concerning the assess-

ment of the system GUI. Finally, the 80% of the sam-

ple judged such interface as simple and very simple to

use.

Figure 8: How do you feel the GUI of the sequencing mod-

ule?

7 CONCLUSIONS AND FUTURE

WORK

In this paper we presented the sequencing module of

the WCB system, capable of helping teachers build-

ing and managing courses composed of Wikipedia

pages. First, registered users are required to in-

sert some topic-terms and secondly to insert some

context-terms both to build the query and to help the

search engine to disambiguate the Wikipedia pages.

Subsequently, the system returns some Wikipedia

pages sequenced by means of the user teaching styles,

according to the Grasha teaching styles model. The

teacher can accept the recommended learning path

or change it both in terms of Wikipedia pages and

in terms of a different learning path. Another im-

portant feature of the system is its ability to man-

age the graph embedding the recommended learning

path proposed by the system: the user can click the

nodes, adding them to the it. All the used pages are

stored in a local database where they are tagged with

the teaching styles of the teacher who used them. In

this way, a CoP can grow and users can beneﬁt of

each others work. Currently the system is at its very

early stage of development, running as a 3-tier web

architecture, developed in java language and using

the wikipedia-miner toolkit to interface itself to the

Wikipedia database. Future work includes a full eval-

uation of all its modules with a large sample.

REFERENCES

Baeza-Yates, R. and Ribeiro-Neto, B. (1999). Modern In-

fromation Retrieval. Addison Wesley.

Baldoni, M., Baroglio, C., Brunkhorst, I., Marengo, E.,

and Patti, V. (2007). Reasoning-based curriculum

sequencing and validation: Integration in a service-

oriented architecture. In Duval, E., Klamma, R., and

Wolpers, M., editors, Creating New Learning Expe-

riences on a Global Scale, volume 4753 of Lecture

Notes in Computer Science, pages 426–431. Springer

Berlin Heidelberg.

Baldoni, M., Baroglio, C., Patti, V., and Torasso, L. (2004).

Reasoning about learning object metadata for adapt-

ing scorm courseware. In Int. Workshop on Engineer-

ing the Adaptive Web, EAW, volume 4, pages 4–13.

Brusilovsky, P. and Vassileva, J. (2003). Course Sequenc-

ing Techniques for Large-Scale Webbased Education.

International Journal of Continuing Engineering Ed-

ucation and Lifelong Learning, 13:75–94.

Brusilowsky, P. (2001). User modeling and user-adapted

interaction. Adaptive hypermedia, 11:87–110.

De Bra, P., Smits, D., and Stash, N. (2006). Creating and

delivering adaptive courses with aha! In Proceedings

of the First European Conference on Technology En-

hanced Learning: Innovative Approaches for Learn-

ing and Knowledge Sharing, EC-TEL’06, pages 21–

33, Berlin, Heidelberg. Springer-Verlag.

Forte, A. and Bruckman, A. (2006). From wikipedia to the

classroom: Exploring online publication and learning.

In Proceedings of the 7th International Conference on

Learning Sciences, ICLS ’06, pages 182–188. Inter-

national Society of the Learning Sciences.

Gabrilovich, E. and Markovitch, S. (2009). Wikipedia-

based semantic interpretation for natural language

processing. J. Artif. Int. Res., 34(1):443–498.

Gasparetti, F., Limongelli, C., and Sciarrone, F. (2015a).

A content-based approach for supporting teachers

in discovering dependency relationships between in-

structional units in distance learning environments.

In Human-Computer Interaction. Theories, Methods,

and Tools - 17th International Conference, HCI Los

Angeles, CA, U.S.A., August 2-7, 2015. To appear.

Gasparetti, F., Limongelli, C., and Sciarrone, F. (2015b).

Exploiting wikipedia for discovering prerequisite re-

lationships among learning objects. In Information

Technology Based Higher Education and Training

(ITHET), 2015 International Conference on. To ap-

pear.

Gasparetti, F., Limongelli, C., and Sciarrone, F. (2015c).

Wiki course builder: a system for retrieving and se-

quencing didactic materials from wikipedia. In In-

formation Technology Based Higher Education and

Training (ITHET), 2015 International Conference on.

To appear.

Grasha, A. (1996). Teaching with style: The integration of

teaching and learning styles in the classroom. Teach-

ing Excellence, 7:31–34.

Limongelli, C., Lombardi, M., Marani, A., and Sciarrone,

F. (2013a). A teacher model to speed up the process

Sequencing Wikipedia Pages: An On-the-ﬂy Approach to Course Building

403

of building courses. In Human-Computer Interaction.

Applications and Services - 15th International Con-

ference, HCI International 2013, Las Vegas, NV, USA,

July 21-26, 2013, Proceedings, Part II, pages 434–

443.

Limongelli, C., Lombardi, M., Marani, A., and Sciarrone, F.

(2013b). A teaching-style based social network for di-

dactic building and sharing. In Artiﬁcial Intelligence

in Education - 16th International Conference, AIED

2013, Memphis, TN, USA, July 9-13, 2013. Proceed-

ings, pages 774–777.

Limongelli, C., Lombardi, M., Marani, A., Sciarrone, F.,

and Temperini, M. (2016). A recommendation mod-

ule to help teachers build courses through the moodle

learning management system. New Review of Hyper-

media and Multimedia, 22(1-2):58–82.

Limongelli, C., Miola, A., Sciarrone, F., and Temperini,

M. (2012a). Supporting teachers to retrieve and se-

lect learning objects for personalized courses in the

moodle ls environment. In The IEEE 14th Interna-

tional Conference on Advanced Learning Technolo-

gies, pages 518–520.

Limongelli, C., Mosiello, G., Panzieri, S., and Sciarrone,

F. (2012b). Virtual industrial training: Joining inno-

vative interfaces with plant modeling. In The 11th

International Conference on Information Technology

Based Higher Education and Training - ITHET 2012,

pages 1–6. IEEE.

Limongelli, C., Sciarrone, F., and Temperini, M. (2015).

A social network-based teacher model to support

course construction. Computers in Human Behavior,

51:1077–1085.

Limongelli, C., Sciarrone, F., Temperini, M., and Vaste, G.

(2009). Adaptive learning with the ls-plan system: A

ﬁeld evaluation. IEEE Transactions on Learning Tech-

nologies, 2(3):203–215.

Milne, D. and Witten, I. H. (2013). An open-source toolkit

for mining wikipedia. Artif. Intell., 194:222–239.

Parker, K. R. and Chao, J. T.(2007). Wiki as a teaching tool.

Interdisciplinary Journal of Knowledge and Learning

Objects, 3:57–72.

Sangineto, E., Capuano, N., Gaeta, M., and Micarelli, A.

(2008). Adaptive course generation through learning

styles representation. Universal Access in the Infor-

mation Society, 7(1-2):1–23.

Sciarrone, F. (2013). An extension of the q diversity met-

ric for information processing in multiple classiﬁer

systems: A ﬁeld evaluation. International Journal

of Wavelets, Multiresolution and Information Process-

ing, 11(6).

Sterbini, A. and Temperini, M. (2013). Openanswer, a

framework to support teacher’s management of open

answers through peer assessment. pages 164–170.

IEEE.

Strube, M. and Ponzetto, S. P. (2006). Wikirelate! com-

puting semantic relatedness using wikipedia. In Pro-

ceedings of the 21st National Conference on Artiﬁcial

Intelligence - Volume 2, AAAI’06, pages 1419–1424.

AAAI Press.

Turchi, T., Malizia, A., Castellucci, P., and Olsen, K.

(2015). Collaborative information seeking with ant

colony ranking in real-time. In 11th Italian Research

Conference on Digital Libraries - IRCDL2015 Bozen-

Bolzano, Italy, 29-30 January, 2015.

Wenger, E. (1998). Communities of practice: Learning as a

social system. Systems thinker, 9(5):2–3.

CSEDU 2016 - 8th International Conference on Computer Supported Education

404