X Framework for Detection, Assessment and Assistance of University Students with Dyslexia and/or Reading Difficulties Carolina Mejía Corredor Girona October 2013
Framework for Detection, Assessment
and Assistance of University Students
with Dyslexia and/or Reading
Difficulties
X
Framework for Detection,
Assessment and Assistance of
University Students with
Dyslexia and/or Reading
Difficulties
Carolina Mejía Corredor
Girona
October 2013
Outline
2
1. Introduction2. Proposal of a framework for detection,
assessment and assistance of university students with dyslexia and/or reading difficulties
3. Detection4. Assessment5. Assistance6. Integration of the framework with a learning
management system7. Conclusions and future work
of university students with reading difficulties
4
Learning Management Systems (LMS)
It is an hypermedia system thatautomates the management ofeducational processes such asteaching and learning.
Adaptive Hypermedia Systems (AHS)
It is an hypermedia system whichreflect some features of the learner ina learner model and apply this modelto adapt visible aspects of the system
to the learner (Brusilovsky, 1996).
Hypermedia System
Learner Model
Adaptation engine
Adaptation
Learner modeling
Motivation
e-learning
5
Adaptation
Learner modeling AHS
LMS Personalization
Research focus
Overall technological-oriented research focus
Motivation
6
Disorders manifested by significant difficulties in the acquisition and use ofreading, writing, spelling, or mathematical abilities (NJCLD, 1994).
Categories of LD
• Children
• Adolescents
• Adults
Types of LD
• Dyslexia
• Dysgraphia
• Dysorthographia
• Dyscalculia
Most common LD in education
MotivationLearning disabilities (LD)
Population under-explored
(University students)
7
Specific reading difficulties which are characterized by:
• difficulties in word recognition,• poor spelling, and• decoding abilities typically result from a phonological deficit.
MotivationDyslexia
Not all students affected with dyslexia are diagnosed before starting their studies at university (Lindgrén, 2012; Löwe & Schulte-Körne, 2004; Wolff, 2006).
reading comprehension reading experience
May include problems in (Lyon, 2003):
8
Dyslexia
Characteristics
Difficulties in reading (e.g., accuracy, decoding words), writing andspelling (Høien & Lundberg, 2000; Lindgrén, 2012).
Associated difficulties (e.g., memory, attention, pronunciation,automation) (Baumel, 2008; Beatty & Davis, 2007; Marken, 2009; Snowling, 2000).
Background of the difficulties (e.g., medical and family history, school life,reading and writing habits, affective and motivational) (Decker, Vogler, &
Defries, 1989; Giménez de la Peña, Buiza, Luque, & López, 2010; Westwood, 2004).
Compensatory strategies (e.g., coping skills, learning styles) (Firth,
Frydenberg, & Greaves, 2008; Lefly & Pennington, 1991; Mellard, Fall, & Woods, 2010).
Deficits in cognitive processes (e.g., phonological and orthograpicalprocessing, lexical access) (De Vega et al., 1990; Fawcett & Nicolson, 1994; Jiménez &
Hernández-Valle, 2000).
Motivation
Dyslexia
Support process
To affected students with dyslexia by means of enabling:
Detection of difficulties related to reading, associated difficulties,background of these difficulties and compensatory strategies, (Giménez de la
Peña et al., 2010; Coffield et al., 2004).
Assessment of cognitive processes (Díaz, 2007; Gregg, 1998; Kaufman, 2000).
Assistance through awareness of difficulties and self-regulation of learning(Goldberg et al., 2003; Raskind et al., 1999; Reiff et al., 1994; Werner, 1993).
Motivation
9
Adaptation
Learner modeling AHS
LMS
10
Overall technological-oriented research focus, with a specific psychological support
Personalization
• Reading difficulties• Associated difficulties• Background• Compensatory strategies• Cognitive processes
Dyslexia characteristics
• Detection• Assessment• Assistance
Dyslexia support process
University student with dyslexia
Motivation
11
Research questionsMain research question
How to include Spanish-speaking university students with dyslexia and/or
reading difficulties in an e-learning process?
12
RQ1. How university students with dyslexia and/or reading difficulties can bedetected?
RQ2. How cognitive traits of the students with dyslexia and/or readingdifficulties can be assessed in order to inquire which cognitiveprocesses related to reading are failing?
RQ3. How university students with dyslexia and/or reading difficulties can beassisted?
RQ4. How the detection, assessment and assistance of university studentswith dyslexia and/or reading difficulties can be provided through anLMS?.
Research questionsSubordinate research questions
13
Including students with dyslexia and/or reading difficulties in an e-learning process,
so as to define methods and tools to detect, assess and assist them in
overcoming their difficulties during their higher education.
ObjectivesMain objective
14
ObjectivesSubordinate objectives
OB.1 Defining a framework for detection, assessment and assistance of universitystudents with dyslexia and/or reading difficulties that can be integrated into aLMS.
OB.6 Integrating the tools developed for the detection, assessment and assistanceof university students with dyslexia and/or reading difficulties with a LMS
OB.5 Analyzing and developing adaptation methods and tools that can be used to
assist university students with dyslexia and/or reading difficulties.
OB.4 Analyzing cognitive processes associated with reading that can be altered inuniversity students with dyslexia and/or reading difficulties in order to develop
methods and tools needed to assess which specific processes are failing.
OB.3 Analyzing and adopting methods and tools for the detection of the learningstyle of university students with dyslexia and/or reading difficulties.
OB.2 Analyzing and developing methods and tools for the detection of university
students with dyslexia and/or reading difficulties.
Methodology
16
Detection
Assessment
Assistance
Demographics• Personal details
• Reading difficulties• Associated difficulties• Background
Reading profile
• Compensatory strategies Learning styles
Cognitive traits• Cognitive processes
Learning analytics
Recommendations
• Awareness• Self-regulation
Learner model
Adaptation engines
Framework
17
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
ENGINES
Web Services
Web Services
Framework
18
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
ENGINES
Web Services
Web Services
OB.1
OB.2
OB.3
OB.4
OB.5
OB.6
19
DetectionLMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
1 ADDA: Autocuestionario de Detección de Dislexia en Adultos2 ADEA: Autocuestionario de Detección del Estilo de Aprendizaje
1
2
Demographics
20
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
Demographics
21
Descriptive data of the personal details of students.
• Sex
• Age
• Country
• City
• Institution
• Academic level
• Academic program
• Course
Web-based forms to capture demographics
Reading profile
22
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
Reading profile
23
Set of characteristics related with the dyslexia (Wolff & Lundberg, 2003).
Self-report questionnaires:• Valid and reliable tools (Gilger, 1992; Lefly & Pennington, 2000). • They allow to collect a big amounts of information in a short time
(Gilger, 1992).• Easy and quick-to-use (Decker, Vogler, & Defries, 1989), but they are unable
to provide a diagnosis (Lyytinen et al., 2006).
There is NOT such a tool standardized to the adult Spanish-speaking population (Giménez de la Peña et al., 2010).
ADDA, a self-report questionnaire to detect dyslexia in adults
24
Case study
Study description
1. Proposing the self-report questionnaire.
2. Estimating the percentage of students that inform of having dyslexia.
3. Knowing the most common difficulties presented by students.
4. Testing the usefulness of the self-report questionnaire.
5. Identifying reading profiles of students.
6. Providing feedback to students.
ADDA:Self-report questionnaire to detect dyslexia in adults
25
Method
Participants:First-year students
N: 513
F: 256M: 257
Age x: 20Sx: 4,3Range: 18-58
Faculties and/or Schools Academic program Frequency Gender %M F
Polytechnic School Architecture 5 5 0 1.0
Electrical Engineering 18 17 1 3.5
Industrial Electronics and Automatic Control Engineering
25 22 3 4.9
Computer Engineering 94 78 16 18.3
Mechanical Engineering 31 26 5 6.0
Chemical Engineering 16 12 4 3.1
Total 189 160 29 36.8
Faculty of Tourism Tourism 15 5 10 2.9
Total 15 5 10 2.9
Faculty of Science Biology 13 4 9 2.5
Biotechnology 10 6 4 1.9
Environmental Sciences 6 2 4 1.2
Chemistry 7 5 2 1.4
Total 36 17 19 7
Faculty of Business andEconomic Sciences
Business Administrationand Management
27 9 18 5.3
Economics 23 14 9 4.5
Total 50 23 27 9.8
Faculty of Law Criminology 30 9 21 5.8
Law 55 21 34 10.7
Total 85 30 55 16.5
Faculty of Education andPsychology
Pedagogy 35 3 32 6.8
Psychology 50 14 36 9.7
Social Work 53 5 48 10.3Total 138 22 116 25.8
Total 513 257 256 100.0
ADDA:Self-report questionnaire to detect dyslexia in adults
Case study
26
Method
Instrument:
1. School and learning to read experience (9 items).
2. History of learning disabilities (6 items).
3. Current reading-writing difficulties (26 items).
4. Associated difficulties (14 items).
5. Family history of learning disabilities (2 items).
6. Reading habits (7 items).
7. Writing habits (3 items).
*Based on ATLAS (Giménez de la Peña et al., 2010).
ADDA:Self-report questionnaire to detect dyslexia in adults
Case study
67 items
27
Method
Procedure:
Form: paper-based and computer-based.
Target: class attending first-year students.
Application: individual.
Responsible: examiner.
Time needed: 20 minutes.
ADDA:Self-report questionnaire to detect dyslexia in adults
Case study
Diagnosis N %
Dyslexia 27 5.26
Dysgraphia/dysorthography 29 5.65
Dyscalculia 3 0.58
Total 59 11,5
28
Results
Percentages
0
10
20
30
40
50
60
70
80 76
6259
39
32
14,8 12,1 11,57,6
N %
• High percentages.• Most common:
dyslexia/dysgraphia/dysorthography
ADDA:Self-report questionnaire to detect dyslexia in adults
Case study
• Few students have been treated.
29
Results
Case study
23,6 23,8 24,6 2528,1
35,7 36,5
46,2
35,730,4
33,928,6
35,7
46,4
0
10
20
30
40
50
60
Sample
Diagnosis
5046,4
Common reading difficulties
Perc
enta
ges
Current reading difficulties
Self-report questionnaire to detect dyslexia in adultsADDA:
30
Results
ADDA:
Reliability
Section Reliability
1. School and learning to read experience. .167
2. History of learning disabilities. .713
3. Current reading-writing difficulties. .842
4. Associated difficulties. .689
5. Family history of learning disabilities. .579
6. Reading habits. .533
7. Writing habits. .576
Total reliability: 0,850
Case study
Self-report questionnaire to detect dyslexia in adults
31
Results
ADDA:
Reading profiles
Profile A: Students reporting current reading difficulties.
Criteria: 5 or more affirmative items in Section 3 (Current difficulties)
Profile B: Normal readers.
Students with profile A were advised to seek assessment to determine whether or not they have dyslexia and to provide specialized help and feedback to overcome their difficulties.
212 (41.3%) Profile A
Case study
Self-report questionnaire to detect dyslexia in adults
32
Discussion
ADDA:
• There was a high percentage of students who reported a previousdiagnosis of learning disabilities (Allor, Fuchs, & Mathes, 2001; Bassi, 2010; Hatcher
et al., 2002; Jameson, 2009; Kalmár, 2011; Madaus, Foley, Mcguire, & Ruban, 2001).
• There was a prevalence of reading and writing as opposed to other typesof disabilities, e.g., mathematics (Díaz, 2007; Gregg, 2007; Roongpraiwan,
Ruangdaraganon, Visudhiphan, & Santikul, 2002; Shaywitz, 2005; Sparks & Lovett, 2010).
• The use of self-report questionnaires could be effective tools to detectstudents with dyslexia (Gilger et al., 1991; Gilger, 1992; Lefly & Pennington, 2000).
Case study
Self-report questionnaire to detect dyslexia in adults
Learning styles
33
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
34
To understand the ways in which students learn, their strengths, their
weaknesses to develop appropriate strategies (Keefe, 1979).
Detecting the learning styles of students with dyslexia can help them toidentify and develop the most effective compensatory strategies theycould use to learn (Coffield et al., 2004; Mortimore, 2008; G. Reid, 2001; Rodríguez,
2004; Scanlon et al., 1998).
There exists different classification proposals for learning styles and several tools to detect them (Coffield et al., 2004; Mortimore, 2008; Rodríguez, 2004).
ADEA, a self-report questionnaire to detect learning styles based on Felder-Silverman’s Index of Learning Styles (ILS)
Learning styles
35
Study description
ADEA:Self-report questionnaire to detect learning styles
Case study
1. Implementing a web-based self-report questionnaire based on Felder-Silverman’s Index of Learning Styles (ILS) (Felder & Silverman, 2002) to detectthe learning styles.
2. Identifying the most preferred learning styles.
3. Inquiring whether or not students were satisfied with their learning style.
36
Method
Participants:
N: 37
F: 19M: 18
Age x: 26Sx: 6,0Range: 21-53
University Frequency Gender %
M F
University of Girona 26 11 15 70.3
University of Córdoba 11 7 4 29.7
Total 37 18 19 100
• All students had a Reading Profile A (detectedwith ADDA).
• 8 students with diagnosis of dyslexia.
Case study
ADEA:Self-report questionnaire to detect learning styles
37
Instrument:
Dimension Learning style
Processing Active
Reflexive
Perception Sensitive
Intuitive
Input Visual
Verbal
Understanding Sequential
Global
The Felder-Silverman’s Index of Learning Styles (ILS) (Felder & Silverman, 2002).
Case study
Method
45 items
Do you agree with your learning style?
44 questions
1 question
ADEA:Self-report questionnaire to detect learning styles
38
Procedure:
Form: computer-based.
Target: voluntary students.
Application: individual.
Responsible: examiner.
Time needed: 20 minutes.
Case study
Method
ADEA:Self-report questionnaire to detect learning styles
39
Results
Case study
Preferred learning styles:
0
10
20
30
40
50
60
70
80
90
100
Active Reflective Sensitive Intuitive Visual Verbal Sequential Global
Processing Perception Input Understanding
100
0
62,5
37,5
100
0
75
25
65,5
34,5
72,4
27,6
82,8
17,2
58,6
41,4
Dyslexic
Posible-dyslexic
Perc
enta
ge
Learning styles
Do you agree with your learning style?............................... YES 94.6%
ADEA:Self-report questionnaire to detect learning styles
40
Discussion
• There was a preference for learning styles Active, Sensitive, Visual, and Sequential (Baldiris, 2012; Graf, 2007; Peña, 2004).
• These results were similar in students with a previous diagnosis of dyslexia (Alty, 2002; Beacham et al., 2003; Mortimore, 2008). They possess a strong visual preference and they process the information actively (Beacham et al., 2003).
• The detection of learning styles could help students with dyslexia to identify effective compensatory strategies (Coffield et al., 2004; Mortimore, 2008; G. Reid,
2001; Rodríguez, 2004; Scanlon et al., 1998).
Case study
ADEA:Self-report questionnaire to detect learning styles
41
DetectLD:
A computer-based tool to manage ADDA and ADEA.
detectLD
Database(Postgres)
Student moduleCreate registerComplete testView result
Teacher moduleCheck testActivate testView result
Expert module
Create/edit testCreate/edit sectionCreate/edit questionCheck testActivate testView result
Web server
(Apache)
PHP
Architecture
Student
Teacher
Expert
Software Tool to Detect Learning Difficulties
42
DetectLD: Software Tool to Detect Learning Difficulties
CreateCheck
Edit/delete
Interfaces
Expertmodule
Teachermodule
View results
43
DetectLD: Software Tool to Detect Learning Difficulties
Interfaces
Register
Self-report questionnaire
Studentmodule
44
AssessmentLMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
ENGINES
Web Services
Web Services
1
1 BEDA: Batería de Evaluación de Dislexia en Adultos
Cognitive traits
45
Characteristics related with the cognitive processes involved in reading. If it is suspected of dyslexia, it is important to have an assessment of these
processes to better understand the problem (Kaufman, 2000).
Batteries are assessment tests (i.e., exercises) proposed to identify learning disabilities such as dyslexia (Santiuste & González-Pérez, 2005).
There are NOT existing tools for the assessment of the cognitive processes in Spanish-speaking adult dyslexic population (Jiménez et al. , 2004).
BEDA, an assessment battery of dyslexia in Spanish-speaking adults
4646
Study description
1. Proposing an automated battery for the assessment of cognitiveprocesses.
2. Evaluating the assessment tasks in a sample of university students.
3. Performing a descriptive analysis of the sample results.
4. Obtaining score scales for the assessment tasks.
5. Analyzing and debugging of the assessment items.
BEDA:Assessment Battery of Dyslexia in Adults
Case study
4747
Method
Participants:
N: 106
F: 49M: 57
Age x: 26Sx: 7,0Range: 19-50
Faculties and/or Schools
Academic program Frequency Gender %M F
Polytechnic School Electrical Engineering 1 1 0 0,9Industrial Electronics and Automatic Control Engineering
1 1 0 0,9
Computer Engineering 16 12 4 15,1Building Engineering 3 2 1 2,8Chemical Engineering 1 1 0 0,9Master 9 7 2 8,5Doctorate 12 11 1 11,3Total 44 35 9 39,6
Faculty of Tourism Advertising and Public Relations 1 0 1 0,9Total 1 0 1 0,9
School of Nursing Master 6 0 6 5,7Total 6 0 6 5,4
Faculty of Business and Economic Sciences
Business Administration and Management
3 1 2 2,8
Accounting and Finance 3 2 1 2,8Economics 2 1 1 1,9Master 2 1 1 1,9Total 10 5 5 9,0
Faculty of Law Political Science and Public Administration
2 1 1 1,9
Law 9 3 6 8,5Total 11 4 7 9,9
Faculty of Education and Psychology
Pedagogy 5 1 4 4,7Pre-School Education 1 0 1 0,9Primary School Education 7 3 4 6,6Psychology 8 3 5 7,5Social Education 5 2 3 4,7Social Work 5 2 3 4,7Master 4 2 2 3,8Total 39 13 26 35,1
Total 106 57 49 100.0
BEDA:Assessment Battery of Dyslexia in Adults
Case study
4848
Method
Instrument:
*Based on UGA Phonological/Orthographic Battery (Gregg, 1998), adapted from Diaz (2007).
BEDA:Assessment Battery of Dyslexia in Adults
Case study
Modules Tasks
Phonological processing 1. Segmentation into syllables (12 items)2. Number of syllables (12 items)3. Segmentation into phonemes (12 items)4. General rhyme (4 items)5. Specific rhyme (18 items)6. Phonemic location (15 items)7. Omission of phonemes (16 items)
Orthographic processing 8. Homophone/pseudohomophone choice (13 items)9. Orthographic choice (18 items)
Lexical access 10. Word reading (32 items)11. Pseudoword reading (48 items)
Processing speed 12. Visual speed (35 items)
Working memory 13. Verbal working memory (18 items)
Semantic processing 14. Reading expository (10 items)15. Narrative texts (10 items)
273 items
4949
Method
Procedure:
Form: computer-based.
Target: voluntary students.
Application: individual.
Responsible: examiner.
Time needed: 50-60 minutes.
BEDA:Assessment Battery of Dyslexia in Adults
Case study
5050
Results
Overall distribution:
Task Mean Median Mode Maximum Minimum Range Variance Std. dev. Skewness Kurtosis1.Segmentation into syllables 0,77 0,92 0,92 1,00 0,00 1,00 0,16 0,39 -1,60 1,732.Number of syllables 0,78 0,88 0,83 1,00 0,00 1,00 0,15 0,38 -1,67 1,863.Segmentation into phonemes 0,82 1,00 1,00 1,00 0,00 1,00 0,14 0,37 -2,03 3,364.General rhyme 0,72 1,00 1,00 1,00 0,00 1,00 0,19 0,43 -1,10 -0,485.Specific rhyme 0,97 1,00 1,00 1,00 0,14 0,86 0,03 0,16 -5,15 35,736.Phonemic location 0,88 0,93 0,93 1,00 0,00 1,00 0,07 0,24 -4,34 24,787.Omission of phonemes 0,78 0,94 0,94 1,00 0,00 1,00 0,15 0,37 -1,89 3,538.Homophone/pseudohomophone choice 0,88 0,92 0,92 1,00 0,00 1,00 0,07 0,25 -4,35 28,269.Orthographic choice 0,84 0,91 0,88 1,00 0,18 0,82 0,10 0,28 -2,11 7,0110.Reading words 0,98 1,00 1,00 1,00 0,25 0,75 0,02 0,11 -5,51 43,4711.Reading pseudowords 0,96 1,00 1,00 1,00 0,00 1,00 0,04 0,18 -6,04 41,5712.Visual speed of letters and numbers 0,95 1,00 1,00 1,00 0,00 1,00 0,05 0,21 -4,95 26,7213.Retaining letters and words 0,93 1,00 1,00 1,00 0,00 1,00 0,07 0,24 -4,12 19,3114.Reading narrative text 0,67 0,80 0,80 1,00 0,00 1,00 0,19 0,43 -1,12 1,0215.Reading expository text 0,63 0,70 0,70 1,00 0,00 1,00 0,21 0,46 -0,62 -1,11
BEDA:Assessment Battery of Dyslexia in Adults
Case study
5151
Results
Score scales:
Phonological processingScalescore
Segmentation into syllables
Number of syllables
Segmentation into phonemes
General rhyme
Specific rhyme
Phonemic location
Omission of phonemes
1 0-1 0-4 0-2 0-1 0-14 0-8 0-12 2 5 3 2 - 9 2-33 3 6 4 3 - - 44 4 - 5 4 15 10 55 5 7 6 5 - 11 6-76 6 8 - 6 - - 8
7 7 - 7 7 16 12 98 8 9 8 8 - - 10-119 9 10 9 9 - 13 12
10 10 - 10 10 17 - 1311 11 11 11 11 - 14 14-1512 12 12 12 12 18 15 16
Orthographic processingScalescore
Homophone/pseudohomophone
choice
Orthographic choice
1 0-8 0-92 - -3 9 104 - 115 10 126 - -7 - 138 11 149 - 15
10 12 -11 - 1612 13 17-18
BEDA:Assessment Battery of Dyslexia in Adults
Case study
Number of intervals = 12
Lexical accessScalescore
Reading words
Reading pseudowords
1 0-25 0-352 26 363 - 37-384 27 395 28 406 - 417 29 428 - 439 30 44-45
10 - 4611 31 4712 32 48
Example:Orthographic processing = 5 + 9 = 14
5252
Results
Score scales:
Scalar sumPercentiles Phonological
processingOrthographical
processingLexical access
Processing speed
Working memory
Semantic processing
1 0-8 0-2 0-2 0-1 0-1 0-23 9 - - - - -5 11 3 3 - - 38 13 - - - - -9 14 4 4 2 2 4
12 16 - - - - -14 18 5 5 - - 518 21 6 6 3 3 623 25 7 7 - - 725 26 - - - - -27 28 8 8 4 4 829 29 - - - - -32 32 9 9 - - 934 33 - - - - -36 35 10 10 5 5 1039 37 - - - - -41 39 11 11 - - 1146 42 12 12 6 6 1250 46 13 13 - - 1353 48 - - - - -55 49 14 14 7 7 1457 51 - - - - -59 52 15 15 - - 1562 55 - - - - -64 56 16 16 8 8 1668 59 17 17 - - 1773 63 18 18 9 9 1875 65 - - - - -77 66 19 19 - - 1980 69 - - - - -82 70 20 20 10 10 2084 72 - - - - -86 73 21 21 - - 2188 75 - - - - -91 77 22 22 11 11 2295 80 23 23 - - 2397 82 - - - - -
100 84 24 24 12 12 24
BEDA:Assessment Battery of Dyslexia in Adults
Case study
Poor performance on reading tests
Poor performance on tests of reading comprehension
Example:Percentile > 25There is NOT deficit
5353
Results
Analysis and debugging of the items:
• Successes/Errors
• Missing
• Difficulty Index (p)
• Levels of difficulty
• Discrimination index (D)
• Levels of discrimination
• Correlations (R)
BEDA:Assessment Battery of Dyslexia in Adults
Case study
273 190 items
Task Initial items Final items1.Segmentation into syllables 12 122.Number of syllables 12 113.Segmentation into phonemes 12 124.General rhyme 4 45.Specific rhyme 18 76.Phonemic location 15 107.Omission of phonemes 16 168.Homophone/pseudohomophone choice 13 79.Orthographic choice 18 1210.Reading words 32 711.Reading pseudowords 48 2512.Visual speed of letters and numbers 35 2713.Retaining letters and words 18 1614.Reading narrative text 10 1015.Reading expository text 10 10
5454
Discussion
• Dyslexia may be caused by a combination of phonological, orthographic, lexical, speed, memory and/or semantic deficits (Booth et al., 2000; Bull & Scerif, 2001;
Marslen-Wilson, 1987; Waters et al., 1984).
• Tasks used to assess each cognitive process were based on related research works in assessing dyslexia in children and adults (Díaz, 2007; E. García, 2004; C. S.
González, Estevez, Muñoz, Moreno, & Alayon, 2004b; D. González et al., 2010; Guzmán et al., 2004; Jiménez
et al., 2004; Jiménez & Ortiz, 1993; Rojas, 2008).
• Debugging of the assessment items was based on correlations, variance,
difficulty index and discrimination index (Díaz, 2007; E. García, 2004).
BEDA:Assessment Battery of Dyslexia in Adults
Case study
55
BEDA
Database(Postgres)
Phonological processing module
Orthographic processing module
Working memory module
Processing speed module
Lexical access module
Semantic processing module
Assessment modules
Management modules
Administration module
Results analysis module
Web server
(Apache)
PHP
BEDA:Assessment Battery of Dyslexia in Adults
Architecture
MUL
T
I
M
O
D
A
L
Student
Teacher
Expert
OutputTextGraphicsAudio
InputSpeechWritingMouseKeyboard
5757
BEDA:Assessment Battery of Dyslexia in Adults
Interfaces
Pedagogical agent
Example itemAssessment item
Assessment modules
5858
BEDA:Assessment Battery of Dyslexia in Adults
Interfaces
Log in
Main menu
Verify item
Management modules
59
AssistanceLMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
1
2
1 PADA: Panel de Analíticas de Aprendizaje de Dislexia en Adultos2 RADA: Recomendador de Actividades para la Dislexia en Adultos
60
Learning analytics
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
Learning analytics
61
Awareness, which leads to reflection on learning, and facilitate self-regulation, are powerful predictors for the academic success (Goldberg et al.,
2003; Raskind et al., 1999; Reiff et al., 1994).
Opening the learner model to students encourages such awareness, reflection and self-regulation of their learning (Bull & Kay, 2008, 2010; Mitrovic &
Martin, 2007).
An emerging technique for the visualization of the learner model is:
Learning Analytics (Hsiao et al., 2010; Verbert et al., 2011).
PADA, a dashboard of learning analytics of dyslexia in adult
62
1. Proposing the dashboard of learning analytics.
2. Answering the next questions:
• Could students view their learner model?
• Could students understand that model?
• Did students agree with the visualizations presented in that model?
• Were students aware on their difficulties, learning styles and cognitive deficits?
• Could PADA support students to perform self-regulated learning?
• Were learning analytics useful for students?
PADA: Dashboard of learning analytics of dyslexia in adults
Case study
Study description
63
N: 26
F: 15M: 11
Age x: 27Sx: 6,8Range: 21-53
•Students had a Reading Profile A (detected with ADDA).•8 students with diagnosis of dyslexia.
PADA: Dashboard of learning analytics of dyslexia in adults
Case study
Method
Participants:
64
PADA: Dashboard of learning analytics of dyslexia in adults
Case study
Method
Instrument:
Descriptive informationDES.1. Have you been diagnosed with dyslexia?NavigationA.1. to A.4. Did you check graphical and textual visualizations in… Tab 1?, Tab 2?, Tab 3, Tab 4?UnderstandingB.1. to B.4. Was it easy for you to understand the meaning of the visualizations displayed on… Tab 1?, Tab 2?, Tab
3?, Tab 4?InspectionC.1. Do you agree with the visualizations about your reading difficulties?C.2. Do you agree with the visualizations about your associated difficulties (i.e., languages, memory, etc.)?C.3. Do you agree with the visualizations about your reading habits?C.4. Do you agree with the visualizations about your writing habits?C.5. Do you agree with the visualizations about your learning style?C.6. Do you agree with the visualizations about your successes/errors in each cognitive assessment task?C.7. Do you agree with the visualizations about your successes/errors in each cognitive process?C.8. Do you agree with the visualizations about your results in the cognitive assessment tasks?C.9. Do you agree with the visualizations about your cognitive deficits?AwarenessD.1. Was it possible for you to be aware about your reading difficulties?D.1.* The former was possible by means of…D.2. Was it possible for you to be aware about your learning style?D.2.* The former was possible by means of…D.3. Was it possible for you to be aware about your cognitive deficits?D.3.* The former was possible by means of…D.4. Was it helpful for your awareness process to view your learning analytics versus the performance of
others (i.e., “peers” and “class”?D.5. Did you learn more about your difficulties than you knew previously?D.6. to D.9. What other visualizations do you think could improve your experience in… Tab 1?, Tab 2?,Tab 3?, Tab 4?Self-regulationE.1. Do you think that PADA can help you in reflecting and making decisions to self-regulate your learning
process?UsefulnessF.1. Was it useful for you to check the visualizations in multiple views (i.e., graphical and textual)?F.2. Did the presented learning analytics provide feedback on your reading performance?F.3. Do you think PADA helps to recognize strengths and weaknesses in your reading process you could use
to improve your academic performance?F.4. Did you find all the visualizations you expected?RecommendationsREC.1. Finally, if you could have a recommender system in PADA, what kind of recommender do you prefer? ‘1
- advices recommended by dyslexia-affected peers’, ‘2 - activities/tasks recommended by expert’, ‘3 -exercises, games, and other resources recommended by experts’.
CommentsCOM.1. Please, if you have more comments about your experience with PADA ...
1. Demographics forms
2. ADDA
3. ADEA
4. BEDA
PADA
Online survey
65
Form: computer-based.
Target: voluntary students.
Application: individual.
Responsible: examiner.
Time needed: 90 minutes.
PADA:Case study
Method
Procedure:
Dashboard of learning analytics of dyslexia in adults
66
PADA: Dashboard of learning analytics of dyslexia in adults
Case study
Results
Navigation:
All students navigated through the different learning analytics.
They only had problems to understand the meaning of the learning analyticsof cognitive processes.
Understanding:
Inspection: Question Responses (n=26) Possible-dyslexic (n=18) Dyslexic (n=8)Strongly disagree
Disagree Indifferent Agree Strongly Agree
M SD M SD
C.1. 0 2 0 12 12 4.44 0.784 4.00 0.926
C.2. 0 1 3 11 11 4.28 0.752 4.13 0.991
C.3. 0 0 3 14 9 4.22 0.732 4.25 0.463
C.4. 0 2 4 11 9 3.94 1.056 4.25 0.463
C.5. 0 0 0 9 17 4.78 0.428 4.38 0.518
C.6. 0 1 3 16 6 4.11 0.832 3.88 0.354
C.7. 0 2 3 13 8 4.11 1.023 3.88 0.354
C.8. 0 2 3 14 7 4.17 0.857 3.63 0.744
C.9. 1 1 0 17 7 4.28 0.752 3.63 1.061
Cognitive processes
67
Question Responses (n=26) Possible-dyslexic (n=18) Dyslexic (n=8)Never Almost
neverSometimes Almost
alwaysAlways M SD M SD
D.1. 1 2 5 7 11 4.00 1.237 3.88 0.991D.2. 0 0 2 5 19 4.72 0.575 4.50 0.756D.3. 2 3 1 12 8 3.78 1.263 3.88 1.246D.4. 0 3 6 4 13 4.11 1.231 3.88 0.835D.5. 0 2 4 12 8 4.22 0.808 3.50 0.926
Question Responses (n=26) Possible-dyslexic (n=18) Dyslexic (n=8)Never Almost
neverSometimes Almost
alwaysAlways M SD M SD
F.1. 0 0 0 3 23 4.94 0.236 4.75 0.463F.2. 1 0 6 13 6 3.94 1.056 3.75 0.463F.3. 0 6 5 8 7 3.72 1.274 3.38 0.744F.4. 0 0 5 16 5 4.22 0.548 3.50 0.535
PADA: Dashboard of learning analytics of dyslexia in adults
Case study
Results
Awareness:
Usefulness:
Expected visualizations
Self-regulation:
61.5% of the students think that PADA could encourage self-regulation in thelearning process.
Increased knowledge
68
• Perceptions of students shown that PADA is reliable, though this claim mayrequire further analysis of the system's confidence (Bull & Pain, 1995; Mabbott &
Bull, 2006).
• It was identified that some dyslexic students did not increase theirawareness because they already knew their particular difficulties sincechildhood (Decker, Vogler & Defries, 1989; Wolff & Lundberg, 2003).
PADA: Dashboard of learning analytics of dyslexia in adults
Case study
Discussion
69
Architecture
•SQL QueriesAggregation
rule
•Self
•Peer
•Class
Social Plane Parameter
•Expert -> Class, peer, self
•Teacher -> Class, peer, self
•Student -> self, peer
Perspective Parameter
Aggregator Elements
Ind
icator
Layer
Co
ntro
lLaye
rSe
man
tic Laye
r
LMS
Inte
rfac
e
Activity-based AggregatorsOutcome-based Aggregators
Data Mining
Learning Analytics Solutions
AJA
X C
alls
Monitor Log / Assessment Results
Sen
sor
Layer
PADA: Dashboard of learning analytics of dyslexia in adults
*Based on AEEA architecture (Florian, 2013).
Forms, ADDA, ADEA,
and BEDAservices
71
PADA: Dashboard of learning analytics of dyslexia in adults
Interfaces
Activity-basedVisualization
Outcome-basedVisualization
73
Recommendations
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
74
RADA, a recommender of activities for dyslexia in adults
RecommendationsGiving hints, feedback, guidance and/or advice support the self-regulation
of the students (Passano, 2000; Santiuste & González-Pérez, 2005).
Recommender system of activities/tasks fed by experts (Mejía, Florian, Vatrapu,
Bull & Fabregat, 2013).
75
1. Proposing the recommendations for students with cognitive deficits.
2. Answering the next questions:
• Did you check recommendations (textual and auditory) when entering RADA?
• Was it easy to understand the recommendations displayed in RADA?
RADA:Recommender of activities for dyslexia in adults
Study description
Case study
76
N: 20
Age x: 24Sx: 2,1Range: 22-27
36 recommendations
Instrument:
RADA:Recommender of activities for dyslexia in adults
Method
Participants:
Case study
Example of recommendation for training SpeedProcessing:“Use video games involving your quick reactionand action. For example, the game “Tetris” orgames in which have time limits for completing atask”.
77
RADA:Recommender of activities for dyslexia in adults
Method
Procedure:
Case study
Form: computer-based.
Target: voluntary students.
Application: individual.
Responsible: examiner.
Time needed: 15 minutes.
78
• All students confirmed they could both hear and read therecommendations.
• Some of the recommendations have to be reviewed and restructured bythe expert psychologists.
RADA:Recommender of activities for dyslexia in adults
Results
Case study
79
IntegrationLMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
80
Framework’s software toolkit
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
Framework’s software toolkit
81
Forms
Tool to capture student’s
demographics
ADEATool to capture
student's learning style
Tool to capture student's
cognitive traits
BEDAADDATool to capture
student's reading profile
PADA
Tool to visualize student's model
RADATool to visualize
student's recommendations
Cognitive processes
Reading aspects
Recommendations
Activity logs
Reading outcomes
Assessment results
UsersRoles &
capabilitiesLearning
style
SOFT
WA
RE
PR
OC
ESS
DA
TAB
ASE
S
Learner Model Adaptation Processes
Registering user, role, age,
academic program, etc.
Detecting particular reading
difficulties
Detecting learning styles
Assessing cognitive processes
Delivering personalized
learning analytics
Delivering personalized
recommendations
Detection Assessment Assistance
82
PIADA’s block
LMS
Personal details tool
Cognitive traits
Reading profile
Learning analytics’ Dashboard
Learning styles
Recommendations
M
U
L
T
I
M
O
D
A
L
M
E
C
H
A
N
I
S
M
S
Learning style tool
Detection
Assessment battery
Recommendationsengine
Reading profile tool
Demographics
Learning analytics engine
Assessment
Assistance
Student
Teacher
Expert
Framework
Forms
PADA
RADA
ADEA
BEDA
ADDAWeb ServicesLEARNER
MODEL
ADAPTATION
PROCESSES
Web Services
Web Services
PIADA: Plataforma de Intervención y Asistenciade Dislexia en Adultos
PIADA’s block
83
Module created in Moodle to integrate the the framework's softwaretoolkit with an LMS.
Moodle:• Great pedagogical and technological flexibility and usability.• Supported by a large community of developers and users.• Developed as an open source educational application.• Simple interface, lightweight, and efficient, which can manage great
amounts of educational resources.• Easy to install.
LMS used at the University of Girona, as well as other universities that have contributed in the development of this research work.
84
MOODLE Framework’s software toolkit
SOAP COMMUNICATION
Remote call
(SOAP libraries)
Publish service
(SOAP libraries)
PIADA block
PIADA’s blockWeb services
Forms
PADA
RADA
ADEA
BEDA
ADDA
How to include Spanish-speaking university students with dyslexia and/or reading difficulties in an e-learning process?
e-Learning
Learning Management System (LMS)
Dyslexia and/or reading
difficulties
Personalization
Learner modeling and adaptation
88
1. A learner model made up of demographics, reading profile, learning styles, and cognitive traits
2. Adaptation engines to deliver learning analytics and specialized recommendations
3. Mechanisms to integrate into an LMS
General summary
Contributions
89
1 Framework
2
3 Software tools
4 Psychometric tools
5 Datasets
•DetectLD
•BEDA, PADA, RADA, and PIADA
•Self-report questionnaire ADDA
•Battery BEDA
•513 university students after ADDA
•119 university students after BEDA
Web-based architectures
General summary
Conclusions
90
RQ.1. How can university students with dyslexia and/or reading difficultiesbe detected?
• Three parallel ways in which the detection could be made.• Self-report questionnaires are useful for detecting students with dyslexia.• ADDA: Self-report questionnaire to detect dyslexia in adults.• Two reading profiles namely: students with and without current difficulties.• Learning styles are useful for identifying compensatory strategies.• Felder-Silverman’s Index of Learning Styles (ILS).
RQ.2. How can cognitive traits of the students with dyslexia and/or readingdifficulties be assessed in order to inquire which cognitive processes relatedto reading are failing?
• Cognitive processes associated with reading.• Batteries useful tools for assessing cognitive processes.• BEDA: Assessment Battery of Dyslexia in Adults.• Valid in terms of content.• First scope of standardization.
91
RQ.3. How can students with dyslexia and/or reading difficulties beassisted? Awareness and self-regulation for the academic successful. Learning analytics for opening the learner model. Dashboards are useful tools for visualizing learning analytics. PADA: Assessment Battery of Dyslexia in Adults. Giving hints, feedback and advice for facilitating self-regulation. RADA: Recommender of activities for dyslexia in adults.
RQ.4. How can the detection, assessment and assistance of universitystudents with dyslexia and/or reading difficulties be provided in a LMS?.
Web services can be used independently from a LMS. Moodle useful tool for integrating the framework. PIADA's block: Block of the Platform for Intervening and Assisting Dyslexia in
Adults.
Conclusions
Future work
92
• Analyzing the tools effectiveness with large samples of university studentswith dyslexia.
• Replicating the findings and validating them in other university contexts.
• Developing improvements of functionalities.
• Creating a tutorial that explains theoretical foundations for teachers andstudents.
• Providing adapted assistance resources and services through an LMS.
Future work
93
• ADDA (Self-report questionnaire to detect dyslexia in adults): studying theinfluence of each section for defining the profiles, consideringmotivational and affective aspects, creating a standardized procedure.
• ADEA (Self-report questionnaire to detect learning styles): identifyingdetailed patterns about the preferences of students with dyslexia.
• BEDA (Assessment Battery of Dyslexia in Adults): converting on apsychometric test standardized.
• PADA (Assessment Battery of Dyslexia in Adults): creating visualizationsthat combine the different aspects of the learner model.
• RADA (Recommender of activities for dyslexia in adults): creating decisionalgorithms for the recommendations engine.
Publications
94
Journal papers• Mejía, C., Florian, B., Vatrapu, R., Bull, S., Fabregat, R. (2013). “A novel web-based approach for visualization
and inspection of reading difficulties on university students”. Computers & Education (Impact Factor: 2.621).Submitted (May 2013).
• Mejía, C., Giménez, A., Fabregat, R. (2013). “Evidence for Reading Disabilities in Spanish University Students– Applying ADDA”. The Scientific World Journal (Impact Factor: 1.730). Submitted (August 2013).
• Mejía, C., Díaz, A., Jiménez, J., Fabregat, R. (2012). “BEDA: a computarized assessment battery for dyslexia inadults”. Journal of Procedia-Social and Behavioral Sciencies, Volume 46, Pages 1795–1800. Published byElsevier Ltd., doi: 10.1016/j.sbspro.2012.05.381.
Book chapters• Díaz, A., Jiménez, J., Mejía, C., Fabregat, R. (2013). “Estandarización de la Batería de Evaluación de la Dislexia
en Adultos (BEDA)”. In M. del C. Pérez Fuentes & M. del M. Molero Jurado (Eds.), Variables Psicológicas yEducativas para la Intervención en el Ámbito Escolar. GEU Editorial.
• Mejía, C., Díaz, A., Jiménez, J., Fabregat, R. (2011). “Considering Cognitive Traits of University Students withDyslexia in the Context of a Learning Management System”. In D.D. Schmorrow and C.M. Fidopiastis (Eds.),Lecture Notes in Computer Science, Volume 6780/2011, Pages 432-441. Published by Springer, doi:10.1007/978-3-642-21852-1_50.
• Baldiris, S., Fabregat, R., Mejía, C., Gómez, S. (2009). “Adaptation Decisions and Profiles Interchange amongOpen Learning Management Systems based on Agent Negotiations and Machine Learning Techniques”. In J.Jacko (Ed.), Lecture Notes in Computer Science (Vol. 5613, pp. 12-20). Springer Berlin / Heidelberg.doi:10.1007/978-3-642-02583-9_2.
Publications
95
Conference papers• Mejía, C., Bull, S., Vatrapu, R., Florian, B., Fabregat, R. (2012). “PADA: a Dashboard of Learning Analytics for
University Students with Dyslexia”. Proceedings of the Last ScandLE Seminar in Copenhagen.
• Mejía, C., Díaz, A., Florian, B., Fabregat, R. (2012). “El uso de las TICs en la construcción de analíticas de aprendizaje para fomentar la autorregulación en estudiantes universitarios con dislexia”. Proceedings of Congreso Internacional EDUTEC 2012, Canarias en tres continentes digitales: educación, TIC, NET-Coaching.
• Mejía, C., Giménez, A., Fabregat, R. (2012). “ATLAS versión 2: una experiencia en la Universitat de Girona”. Proceedings of the XXVIII Congreso Internacional AELFA: Asociación Española de Logopedia, Foniatría y Audiología.
• Mejía, C., Fabregat, R. (2012). “Framework for Intervention and Assistance in University Students with Dyslexia”. In Bob Werner (Eds). Proceedings of the 12th IEEE International Conference on Advanced Learning Technologies (ICALT 2012), Volume 2012, pp. 342-343. Rome, Italy.
• Mejía, C., Clara, J., Fabregat, R. (2011). “detectLD: Detecting University Students with Learning Disabilities in Reading and Writing in the Spanish Language”. In T. Bastiaens & M. Ebner (Eds.), Proceedings of World Conference on Educational Multimedia, Hypermedia and Telecommunications 2011 (ED-MEDIA 2011), Volume 2011, Issue 1, pp. 1122-1131, Chesapeake, VA: AACE. Lisboa, Portugal.
• Gelvez, L., Mejía, C., Peña, C.I., Fabregat, R. (2010). “Metodología de Gestión de Proyectos aplicada al Desarrollo de Objetos de Aprendizaje”. In J. Sánchez, Congreso Iberoamericano de Informática Educativa (Vol. 1, pp. 690-697). Santiago de Chile, Chile.
• Mejía, C., Fabregat, R., Marzo, J.L. (2010). “Including Student's Learning Difficulties in the User Model of a Learning Management System”. XXXVI Conferencia Latinoamericana de Informática (CLEI 2010) (pp. 845-858). Asunción, Paraguay.
Publications
96
Conference papers• Mejía, C., Fabregat, R. (2010). “Towards a Learning Management System that Supports Learning Difficulties
of the Students”. In P. Rodriguez (Ed.), XI Simposio Nacional de Tecnologías de la Información y lasComunicaciones en la Educación (ADIE), SINTICE 2010 (pp. 37-44). Ibergarceta Publicaciones , S.L. Valencia,Spain.
• Mejía, C., Baldiris, S., Gómez, S., Fabregat, R. (2009). “Personalization of E-Learning Platforms Based On anAdaptation Process Supported on IMS-LIP and IMS-LD”. In I. Gibson, R. Weber, K. McFerrin, R. Carlsen, & D. A.Willis (Eds.), Society for Information Technology & Teacher Education International Conference 2009 (pp.2882-2887). Charleston, SC, USA: AACE.
• Mejía, C., Mancera, L., Gómez, S., Baldiris, S., Fabregat, R. (2008). “Supporting Competence upon dotLRNthrought Personalization”. 7th OpenACS / .LRN conference (pp. 104-110). Valencia, Spain.
• Mejía, C., Baldiris, S., Gómez, S., Fabregat, R. (2008). “Adaptation Process to Deliver Content based on UserLearning Styles”. In L. Gómez Chova, D. Martí Belenguer & I. Candel Torres (Eds.), International Conference ofEducation, Research and Innovation (ICERI 2008) (pp. 5091-5100). International Association of Technology,Education and Development (IATED). Madrid, Spain.
Guides & reports• Díaz, A., Mejía, C., Jiménez, J., Fabregat, R. (2012). “Manual de uso e instrucciones de la batería de
evaluación de dislexia en adultos (BEDA)”. Universitat de Girona (27 p.), unpublished, Girona (Spain).
• Mejía, C., Díaz, A., Jiménez, J., Fabregat, R. (2012). “Manual de instalación de la Batería de Evaluación de Dislexia en Adultos (BEDA)”. Universitat de Girona (5 p.), unpublished, Girona (Spain).
Publications
97
Final thesis reports • Co-director of the bachelor’s degree project: “Integration of a framework for intervention and assistance of
students with reading difficulties with the e-learning platform MOODLE”, developed by Marco Caballero, Randy Espitia, Julio Martinez. University of Córdoba, Colombia, 2013.
• Co-director of the bachelor’s degree project: “Design and implementation of a system for detection of students with learning disabilities in reading and identification of cognitive processes deficient”, developed by Jonathan Clara. University of Girona, Spain, 2011.
Invited talks • Mejía, C. “Framework per a personalitzar la intervenció i assistència per a estudiants amb dislèxia a través
d’un sistema de gestió de l’aprenentatge”. In FEDER project reports – Clúster TIC MEDIA de Girona,presented at Jornades de Creació d'Objectes d'Aprenentatge Adaptatius: l’Ajuntament de Girona. 2011.Girona, Spain.
• Gómez, S., Mejía, C. Construcción de Unidades de Aprendizaje Adaptativas basada en el Contexto de Acceso.I Congreso Internacional de Ambientes Virtuales de Aprendizaje Adaptativos y Accesibles - Competenciaspara Todos (CAVA3). 2009. Montería, Colombia.
• Mejia, C., Gomez, S., Huerva, D. Adaptation Process in E-Learning Platforms. BCDS International Workshop.2008. Girona, Spain.
Publications
98
Scientific collaborations • Collaborative work initiative for the development of PADA with the Computational Social Science Laboratory
(CSSL) from the Copenhagen Business School (Denmark), the Open Learner Modeling Research Group fromthe University of Birmingham (UK), and the Department of Education at the University of La Palmas de GranCanarias (Spain). 2013.
• Collaborative work initiative for the development of BEDA with the Research Group on Learning Disabilities,Psycholinguistics and New Technologies (DEA&NT) from University of La Laguna (Spain). 2012.
• Collaborative work initiative for the development of ADDA with the University of Girona (Spain), and theDepartment of Psychology from University of Malaga (Spain). 2011.
Framework for Detection, Assessment
and Assistance of University Students
with Dyslexia and/or Reading
Difficulties
Framework for Detection, Assessment and
Assistance of University Students with Dyslexia
and/or Reading Difficulties
THANK YOU
Girona
October 2013