Según las categorías presentadas en el taller 2, aqui estan los articulos que se usarán en el estado del

arte para, estos documentos presentan métodos, estrategias y modelos de herramientas basadas en
CSCL para el CS1

CATEGORY: Only Computer-Supported Collaborative Learning (CSCL)

Perspectives on Tools for Computer-Supported Collaborative Learning

Abstract: ​Computer Supported Collaborative Learning CSCL is a research field which emerged during the past
20 years. The research addressed questions in CSCL including-among others-how groups and individuals learn
through peer interaction using specific tools, how small groups interact and develop shared meanings over time,
how teachers orchestrate collaborative learning activities in the classroom with the support of technology, how
institutions change and create new conditions for teaching and learning, and even how the opportunities for
learning change as society adopts new models for education. Following the constructivistic and socio-cultural
approaches in learning, numerous CSCL tools have been designed, developed and tested over the years.
Although they can be classified in various ways, the distinction between systemic and dialogic types of tools and
approaches is adopted in this paper. Following this categorization, four interesting research approaches, each
focusing on a different kind of computer mediated tool are presented, designating the diversity of research within
the CSCL field.

Adaptive and Intelligent Systems for Collaborative Learning Support: A Review of the Field
Anastract: This study critically reviews the recently published scientific literature on the design and impact of
adaptive and intelligent systems for collaborative learning support (AICLS) systems. The focus is threefold: 1)
analyze critical design issues of AICLS systems and organize them under a unifying classification scheme, 2)
present research evidence on the impact of these systems on student learning, and 3) identify current trends and
open research questions in the field. After systematically searching online bibliographic databases, 105 articles
were included in the review with 70 of them reporting concrete evaluation data on the learning impact of AICLS
systems. Systems design analysis led us to propose a classification scheme with five dimensions: pedagogical
objective, target of adaptation, modeling, technology, and design space. The reviewed articles indicate that
AICLS systems increasingly introduce Artificial Intelligence and Web 2.0 techniques to support pretask
interventions, in-task peer interactions, and learning domain-specific activities. Findings also suggest that AICLS
systems may improve both learners’ domain knowledge and collaboration skills. However, these benefits are
subject to the learning design and the capability of AICLS to adapt and intervene in an unobtrusive way. Finally,
providing peer interaction support seems to motivate students and improve collaboration and learning.

Integrating Educational Tools for Collaborative Computer Programming Learning

Abstract: Computer Programming learning is a difficult process. Experience has demonstrated that many
students find it difficult to use programming languages to write programs that solve problems. In this paper we
describe several educational computer tools used successfully to support Programming learning and we present
a global environment which integrates them, allowing a broader approach to Programming teaching and learning.
This environment uses program animation and the Computer-Supported Collaborative Learning (CSCL)
paradigm.

Survey of intelligent collaborative E-learning systems

Abstract​: ​In recent years, agent technology is used to design solutions that facilitate the implementation of new
concepts, especially in the field of E-learning. It is widely used to model the different actors of E-learning systems
and manage their interactions, to meet their dynamic and execution needs by their innovative features like
intelligence and autonomy. In education field, multi-agent systems makes a great change in the society in the fact
that the conventional education system requires the presence of both student and instructor at same place, the
same time and at the same interval of time. This kind of system equips with these characters; and provides many
advantages like autonomy, reactivity, social ability and proactivity. There are several collaborative E-learning
environments using multi-agent technologies that included I-MIND, MASCE, ALLEGRO, etc. Our work aims to
define the importance of a collaborative learning system, to define the roles of each actor and the different
possible communications between them, to determine the tasks of the agents that can be automated.
Furthermore, an analysis of existing multi-agent based collaborative E-learning systems on the basis of their
various features covering collaboration features, student tutor interaction, adaptability measurement and security
in order to identify your strengths and weaknesses to determine the most suitable model to our system.

CATEGORY: Only Computer-Supported Collaborative Learning (CSCL) with-for-in CS1

I-MINDS: A Multiagent System for Intelligent Computer- Supported Collaborative Learning and Classroom
Management
Abstract: I-MINDS provides a computer-supported collaborative learning (CSCL) infrastructure and environment
for learners in synchronous learning and classroom management applications for instructors, for large classroom
or distance education situations. For supporting the instructor, I-MINDS includes a teacher agent. The teacher
agent allows the instructor to interact with students, manage Q&A sessions, administer quizzes, post evaluations,
form groups and monitor individual and group performances. For computer-supported collaborative learning,
I-MINDS, which stands for Intelligent Multiagent Infrastructure for Distributed Systems in Education, provides a
student agent for each student. Each student agent monitors and models its user and carries out group formation
with other student agents behind-the-scene. I-MINDS provides standard online collaborative features such as
chat rooms and whiteboards and implements a structured cooperative learning mechanism called Jigsaw. The
system also incorporates multiagent coalition formation algorithms for forming peer groups.

A computer-supported cooperative learning system with multiagent intelligence

Abstract: In this paper, we describe an innovative infrastructure to support student participation and collaboration
and help the instructor manage large or distance classrooms using multiagent system intelligence. The system,
called I-MINDS, has a host of intelligent agents for each classroom: a teacher agent ranks and categorizes
real-time questions from the students and collects statistics on student participation, a number of group agents
that each maintains a collaborative group and facilitate student discussions, and a student agent for each student
that profiles a student and finds compatible students to form the student's "buddy group". Each agent is capable
of machine learning, thus improving its performance and services over time. These agents also interact and
collaborate among themselves to exchange information and form coalitions dynamically to better serve the users.
We have pilot-tested I-MINDS in GIS lectures, deployed I-MINDS in an introductory computer science course
(CS1)'s laboratory, and evaluated the impact of I-MINDS based on student assessment. The results showed that
students using I-MINDS performed (and outperformed in some aspects) as well as students in traditional settings.

Lessons Learned from Comprehensive Deployments of Multiagent CSCL Applications I-MINDS and
ClassroomWiki
Abstract: We have used a multiagent-based system to develop a CSCL application and multiagent-frameworks to
form student groups that improve student collaborative learning. In this paper, we describe the contexts of our
three generations of CSCL applications (i.e., I-MINDS and ClassroomWiki) and provide a set of lessons learned
from our deployments in terms of the script, tool, and pedagogical aspects of using CSCL. We believe that our
lessons would allow 1) the instructors and students to use intelligent CSCL applications more effectively and
efficiently, and help to improve the design of such systems, and 2) the researchers to gain additional insights into
the impact of collaborative learning theories when they are applied to real-world classrooms.

Statistics and analysis tools for a computer-supported collaborative learning system

Abstract: ur virtual classroom analysis tool derives statistics from these interactions such as student
responsiveness, degree of dialog involvement, amount of contribution, and quality of involvement and
contribution. Then, an instructor can view overall trends for individual students and groups and detailed charts for
all statistics for each student or all students for each statistic, which is especially helpful in large classrooms and
in distance education. The instructor can also adjust a "highlight" threshold for each statistic such that any value
failing to meet the threshold will be highlighted for easy observation. Our Database Search analysis tool allows
students and teachers to search through recorded interactions and filter the results based on metadata such as
time interval, class relevance, or keyword content.

Computer-Supported Structured Cooperative Learning

Abstract: In this paper we describe computer-supported structured cooperative learning, applied to the
laboratories of an introductory CS1 course. We extended IMINDS, a multiagent system that supports
student-teacher and student-student realtime interactions, to support a cooperative learning paradigm called
Jigsaw.

SMAS: A solution-based multi-agent system for improving problem solving skills in computer
programming
abstract: In this research, a solution-based multi-agent system (SMAS) is proposed, which benefits from a novel
automatic text to-flow chart conversion approach in order to improve students problem solving skills. The aim is
to introduce the early stages of learning programming (CS1). By using SMAS, students can focus on solution
designing activities in the form of flowchart development more than on language and syntax. Ultimately, an
experimental study is devised to assess the success of SMAS as a tool to aid students with problem solving
activities and learning computer programming. In total, 30.4% of problems that were left unresolved in previous
sessions were solved by students in the control group, whereas 69.7% of previously unresolved problems were
solved by students in the experimental group who used SMAS.
Therefore, the use of SMAS in practice is supported, as the results indicate considerable gains for the
experimental group over the control group.

CATEGORY: formation of programming groups and assessment in CSCL

Investigating Differences in Wiki-based Collaborative Activities between Student Engagement Profiles in

CS1
Introductory computer science courses are being increasingly taught using technology-mediated instruction and
e-learning environments. The software and technology in such courses could benefit from the use of student
models to inform and guide customized support tailored to the needs of individual students. In this paper, we
investigate how student motivated engagement profiles developed in educational research can be used as such
models to predict student behaviors. These models are advantageous over those learned directly from observing
individual students, as they rely on different data that can be available a priori before students use the
technology. Using tracked behaviors of 249 students from 7 CS1 courses over the span of 3 semesters, we
discover that students with different engagement profiles indeed behave differently in an online, wiki-based CSCL
system while performing collaborative creative thinking exercises, and the differences between students are
primarily as expected based on the differences in the profiles. Thus, such profiles could be useful as student
models for providing customized support in e-learning environments in CS1 courses.

A Memetic Algorithm for Collaborative Learning Team Formation in the Context of Software Engineering
Courses

Abstract: In this paper, we propose a memetic algorithm with the aim of assisting professors when forming
collaborative learning teams in the context of software engineering courses. This algorithm designs different
alternatives to divide a given number of students into teams and evaluates each alternative as regards one of the
grouping criteria most analyzed and appropriate in the context of software engineering courses. This criterion is
based on taking into account the team roles of the students and on forming well-balanced teams according to the
team roles of their members. To analyze the performance of the proposed algorithm, we report the computational
experiments developed on eight different data sets. In this respect, the algorithm has obtained high-quality
solutions for each one of the utilized data sets.

An evaluation of students’ motivation in computer-supported collaborative learning of programming

concepts

Abstract: Motivation is a very important factor for successful instruction. This factor is especially relevant in
collaborative learning contexts, where social interaction plays an important role. In this paper we present an
evaluation of motivation in 139 students who were instructed under four pedagogical approaches: traditional
lecture, collaborative learning, collaborative learning guided by CIF (an instructional framework for collaborative
learning), and collaborative learning guided by CIF and supported by MoCAS (a collaborative learning tool). We
considered the four dimensions of motivation according to self-determination theory. The statistical results show
that, in global terms, students were more motivated by jointly using the collaborative instructional approach CIF
and the MoCAS tool than by using a collaborative approach. Detailed analysis of the different kinds of motivation
yields mixed results. Students who were instructed with CIF and especially those students instructed with CIF
and MoCAS exhibited higher intrinsic motivation. Furthermore, students instructed with CIF and MoCAS were the
most extrinsically motivated via identified regulation. With respect to extrinsic motivation via external regulation,
students instructed in a traditional, individual way were more motivated than students instructed collaboratively.
Finally, high levels of amotivation were also associated to instruction using CIF and MoCAS.

Idea del proyecto

Los estudiantes en aulas grandes o distantes a menudo no disfrutan del mismo nivel y calidad de las
interacciones entre alumnos y estudiantes e instructores durante la clase (sincrónicamente) o después de la
clase (de forma asíncrona) que en salones de clase más pequeños. Sin embargo, tales interacciones son
importantes para fomentar el aprendizaje en grupo y la afinidad de los estudiantes en una clase. Para mejorar
tales interacciones, los educadores han recurrido a la tecnología, como los sistemas de respuesta personal, las
salas de chat en línea, las herramientas de teleconferencia y los entornos de aprendizaje colaborativo asistido
por computadora (CSCL). Sin embargo, la mayoría de los sistemas CSCL, no se adaptan a las diversas
necesidades y comportamientos de los estudiantes e instructores : son participantes pasivos en el proceso y los
estudiantes e instructores a menudo recurren a otros modos de interacción (correo electrónico, teléfono o
reuniones cara a cara) para abordar problemas individuales. Además, el advenimiento de la tecnología de
Internet y multimedia ha significado cambios drásticos en el proceso de enseñanza y aprendizaje, desde el aula
tradicional hasta una distribución más virtual, virtual pero aún interactiva. Por lo tanto, hay motivación y
oportunidad para desarrollar sistemas CSCL inteligentes.

Lo anterior da paso a este trabajo investigativo donde se planea: diseñar un modelo que permita la integración
de multiagentes CSCL apoyado con técnicas computacionales, que permita al docente y estudiantes, 1) percibir
su entorno y responder de manera oportuna a los cambios que se producen en él, 2) exhibir conductas dirigidas
a los objetivos al tomar la iniciativa y 3) interactuar Con otros agentes y usuarios humanos.

El modelo será probado en una herramienta que de debe contar con estos principios:

Principio 1. Primero, queremos construir un sistema CSCL que sea sensible, flexible, distribuido y adaptable a
los comportamientos individuales de los estudiantes. La necesidad de un marco flexible y adaptable surge de la
diversidad en la capacidad y motivaciones de los estudiantes que participan en un entorno típico de CSCL. Un
marco distribuido distribuiría los requisitos de recursos computacionales y, como resultado, haría que el sistema
sea más sensible y tolerante a fallos.

Principio 2. En segundo lugar, queremos construir un sistema CSCL que sea capaz de evolucionar con el tiempo
en términos de su conocimiento pedagógico, el modelado de estudiantes e incluso grupos, y el desempeño en el
apoyo a las decisiones. Los usuarios humanos varían en su nivel de habilidad, motivación, conocimiento,
experiencia, etc. Por lo tanto, una solución o marco no adaptativo para CSCL que funciona para un tipo de
estudiante puede no funcionar para los demás.

Principio 3. En tercer lugar, queremos construir un sistema CSCL que sea capaz de formar grupos de
aprendizaje de estudiantes efectivos por sí solo. Una capacidad de formación de grupos de aprendices
automatizada facilita que el instructor lleve a cabo actividades de grupo en un aula grande.

El desarrollo de un entorno CSCL para alumnos en aplicaciones de aprendizaje sincrónico y de gestión de

clases para instructores, para situaciones de grandes aulas o educación a distancia. Para apoyar al instructor
construir un agente maestro. un agente docente que permita que el instructor interactúe con los estudiantes,
administre sesiones de preguntas y respuestas, administre exámenes, publique evaluaciones, forme grupos y
monitoree actuaciones individuales y grupales. Para el aprendizaje colaborativo asistido por computadora, que
para este caso sería: Infraestructura Multiagente Inteligente para Sistemas Distribuidos en Educación, construir
un agente estudiantil para cada estudiante. Cada agente estudiantil monitorea y modela a su usuario y lleva a
cabo la formación de grupos con otros agentes estudiantiles detrás de la escena o el proceso.

implementar en el sistema herramientas características de colaboración en línea estándar, como salas de chat y
pizarras, e implementa un mecanismo de aprendizaje cooperativo estructurado como Jigsaw. El sistema también
incorpora algoritmos de formación de coalición multiagente para la formación. creación de un agente de grupo
para cada grupo de pares que supervisa y evalúa su grupo de pares asignado.

Los resultados que arrojen las herramientas inteligentes integradas mostrarán métricas en un entorno de
tiempo real para apoyar las actividades de aprendizaje cooperativo de los estudiantes, y también como un banco
de pruebas para recopilar datos instructivos o pedagógicos para una mejor comprensión del aprendizaje
colaborativo de los estudiantes.