Collaborative learning in postgraduate level courses

Computers in Human Behavior 51 (2015) 938–944

Contents lists available at ScienceDirect

Computers in Human Behavior journal homepage: www.elsevier.com/locate/comphumbeh

Collaborative learning in postgraduate level courses Itzamá López-Yáñez a, Cornelio Yáñez-Márquez b,⇑, Oscar Camacho-Nieto a, Mario Aldape-Pérez a, Amadeo-José Argüelles-Cruz b a Instituto Politécnico Nacional, Centro de Innovación y Desarrollo Tecnológico en Cómputo IPN-CIDETEC, Av. Juan de Dios Bátiz, Esq. Miguel Othón de Mendizábal, CIDETEC Building, Mexico City 07738, Mexico b Instituto Politécnico Nacional, Centro de Investigación en Computación IPN-CIC, Av. Juan de Dios Bátiz, Esq. Miguel Othón de Mendizábal, CIC Building, Mexico City 07738, Mexico

a r t i c l e

i n f o

Article history: Available online 12 December 2014 Keywords: Collaborative learning Postgraduate level courses Mobile learning Mobile networks Social networks

a b s t r a c t Nowadays, we are immersed in the social and mobile networks era. As a positive consequence of this, collaborative and mobile learning in educational environments have been encouraged thanks to the use of computing for human learning. By coupling the advantages of collaborative and mobile learning, the teaching-learning processes involved in postgraduate courses may be greatly enhanced. The pedagogical experiences in this regard lived by the authors in the Alpha–Beta Research Group when coupling collaborative and mobile learning in the context of postgraduate level courses, are presented in this paper. Ó 2014 Elsevier Ltd. All rights reserved.

1. Introduction The social and mobile networks era has caught up with us. Impressive technological advances are already here, generating drastic changes in our day-to-day activities. In educational environments, collaborative and mobile learning have been encouraged due to the use of computing for human learning. According to Lehtinen, Hakkarainen, Lipponen, Rahikainen, and Muukkonen (1999), one of the prime goals of education in the near future will be to enable learners to actively participate in an interconnected society, whose main resource for development (either personal, social, or economical) will be knowledge. The challenges implied by such requirement have pushed educational institutions to find, develop, and implement new appropriate pedagogical methods. It is understood that computers could play an important role in restructuring and developing teaching and learning processes to be better prepared for future challenges. One of the most promising concepts arising from such developments is computersupported collaborative learning. Clearly, these authors correctly perceived, before the onset of the new millennium, the relevant role played by computer-supported collaborative learning in educative contexts. On the other hand, a lot of contemporary authors refer to the importance of the modern educational technologies. For example, Webster and Murphy (2008) state that novel technologies present ⇑ Corresponding author. Tel.: +52 5557296000x56584, +52 5528885118. E-mail addresses: [email protected] (I. López-Yáñez), [email protected], [email protected] (C. Yáñez-Márquez), [email protected] (O. Camacho-Nieto), [email protected] (M. Aldape-Pérez), [email protected] (A.-J. Argüelles-Cruz). http://dx.doi.org/10.1016/j.chb.2014.11.055 0747-5632/Ó 2014 Elsevier Ltd. All rights reserved.

research opportunities for the teaching and learning processes. In this sense, the challenges to learning with technology include open source software developments, social networking tools, mobile devices, and management systems. However, achieving a balance between these and other factors presents a challenge to all educators. The authors conclude that the institutions can act strategically to both encourage innovation and—at the same time—ensure that the technological underpinnings of the learning and teaching environment are stable and supportive. In regards to this line of thought (which serves as support in our research) we shall mention two recent works of strategic importance. On one hand, Bottino (2012) expresses some notions and perspectives about framing technology enhanced learning environments, with a vision according to our work premises. On the other hand, Benson, Morgan, and Tennakoon (2012) present a framework for knowledge management in higher education, which we have taken into account in formulating our pedagogical experiences. An emerging concept coupled with social and mobile networks is that of Semantic Web, whose importance is highlighted by such authors as Vossen, Lytras, and Koudas (2007). They express that the concept of semantics and its capacity to support a new era of applications challenges the traditional perceptions for the neverending journey of computing. These authors even claim that knowledge and data representation, as well as retrieval, require new conceptual models and the move to a human Semantic Web vision seems timelier than ever. On the same proverbial page, Lytras and de Pablos (2009) establish that, as semantic technologies prove their value with targeted computing solutions, there are increasing opportunities to consider their application in social contexts for knowledge, learning, and

I. López-Yáñez et al. / Computers in Human Behavior 51 (2015) 938–944

human development. These kinds of novel technologies are able also to enable a better use of intellectual assets, in addition to which many governments are forced to increasingly deal with knowledge services that form larger parts of the current and future global economy and society. The influence of the modern educational technologies has been so pervasive that it has even given rise to a strong debate between specialist: on one hand, there are those who favor information technologies as a technical and functional expression of modernity (the Accolatory), and on the other hand (the Dismissive) there are those who protest the use and abuse of information technologies. Aside from this debate, it is publicly known that both students and mentors make everyday use of this kind of educational technologies (Moreno-Moreno & Yáñez-Márquez, 2008; Yáñez-Márquez, Aldape-Pérez, López-Yáñez, & Camacho-Nieto, 2014). Lytras and de Pablos (2011) posit that software technologies can play a critical role towards the evolution and innovation of state of the art approaches to well-known deficits of performance in knowledge generation and management. Then, they establish the following open question, in the knowledge society context: how can ideas and abstractions about effective solutions be transformed to functional solutions? With respect to social and mobile networks, Alexander (2004) and Traxler (2007) note that the socializing power of mobility could bring about collaborative learning and that in these new environments, mobile learning allows students to access academic online resources from any location, at any given time, thanks to the use of mobile devices in social networks. In the current paper, the pedagogical experiences lived by the authors in the Alpha–Beta Research Group when coupling collaborative and mobile learning in the context of postgraduate level courses, are presented. The rest of this paper is organized as follows: Section 2 is dedicated to describing the nature and basic concepts about collaborative and mobile learning. The third section describes technological advances in educational environments, namely repositories and tools. Pedagogical experiences are presented in Section 4, and a discussion of related works in Section 5; leaving conclusions and future work for Section 6, and finally the references are included. 2. Collaborative and mobile learning In this section, the nature, development and basic concepts about collaborative and mobile learning are described. In this regard, it is convenient to part from the interesting concepts and ideas included in Lytras and Kurilovas (2014), which are framed in a special edition whose topic is information and communication technologies for human capital development. In this context, the authors state that in the last decade, the appearance and evolution of emerging technologies have given rise to a new environment for using human behavior as a basis for knowledge and learning intensive settings. They claim to have found six technologies with a marked influence in the development of contemporary scientific research, among which learning technologies stand out. In particular, new forms of collaborative development of knowledge and learning objects bases promote further the understanding of how people construct, structure, and reuse knowledge. Further, the authors propose that mobile learning, along with flexible infrastructures using portable smart devices, is quite adequate for the diffusion of micro-content and micro-blogging components to learners on demand. 2.1. Collaborative learning The concept of collaborative learning is essential for this work, since the Alpha–Beta Research Group is very interested in coupling

939

collaborative and mobile learning in the context of postgraduate level courses. Dillenbourg (1999) provides a very broad definition of collaborative learning, as a situation in which two or more people attempt to learn something together. Notice that, in this definition, particular forms of interaction (triggering learning mechanisms) are expected, yet not guaranteed. Thus, a general concern in collaborative learning is to improve the probability of interactions which enable learning happen. Regarding the approaches underpinning the existence and use of collaborative learning, Zurita and Nussbaum (2004) claim that collaborative learning is considered to enable cognitive development, since it stimulates social interaction and learning among the members of a group. In this regard, two major theoretical approaches explain the role of social interaction in collaborative learning. On one hand, the Vygotskian perspective considers that individual change arises as the result of an internalization of regulatory activities, such as member coordination and interaction of constructive processes, achieved by the mediation of communication between them. On the other hand, the Piagetian approach posits that collaborative learning is effective because it promotes the emergence of socio-cognitive conflicts due to different opinions and strategies employed by the partners. Independently from the adopted theoretical approach, the members of the Alpha–Beta Research Group are convinced of the benefits of adopting collaborative learning in postgraduate level courses, as Roberts (2005) highlights: Academic benefits: promotes critical thinking skills by through discussion and debate; involves students actively in the learning process by creating an environment of active, involved, exploratory learning; improves classroom results by promoting higher achievement and class attendance, as well as innovation in teaching and classroom techniques; and fosters the development of problem solving techniques, potentially helping weaker students improve their performance when grouped with higher achieving students. Social benefits: develops a social support system for students; builds diversity understanding among students and staff; and establishes a positive atmosphere for modeling and practicing cooperation, as well as team work. Psychological benefits: can help to reduce anxiety and encourage students to seek help and accept tutoring from their peers; and develops positive attitudes towards teachers. The benefits of collaborative learning within a computer-supported environment can be at least as great as those within a classroom or lecture hall. In an asynchronous environment, students do not need to meet at a regular place at regular times, so ‘‘missing a session’’ has a lesser impact. Fruitful and constructive discussion and dialogue can take place at any time of the day or night, whenever inspiration or enthusiasm strikes. Good ideas are less likely to be lost, and thoughts can be followed through without regard to the normal time constraints. Opinions can be considered on their merits, without some of the stereotypical assumptions that may be superimposed in a face-to-face environment based on the speaker’s gender or physical appearance. Based on the former concepts, the members of the Alpha–Beta Research Group have strongly incorporated practices inherent to collaborative learning in their academic tasks, with highly encouraging results. 2.2. Mobile learning The concept of mobile learning, in the context of the current paper, is considered as a relevant complement to collaborative learning, especially when applied in postgraduate level courses at the Alpha–Beta Research Group.

940


According to Kearney, Schuck, Burden, and Aubusson (2012), mobile learning has three features which characterize this new paradigm: authenticity, collaboration and personalization. In this context, Sharples, Taylor, and Vavoula (2005) have established some conclusions about the features of mobile learning, which concerns the way in which the combination of wireless technology and mobile computing is resulting in escalating transformations of the educational world (Alexander, 2004). Besides, this concept involves the nexus between working with mobile devices and the occurrence of learning: the process of learning mediated by a mobile device. Following Kukulska-Hulme (2010), mobile learning challenges us to create new learning, in the form of: new content, interactivity, supporting media (or multimedia), and knowledge sharing. Thus, mobile learning unavoidably leads to e-learning content exploitation. The latter is related to the appearance of several lines of research, focused on developing a framework for analyzing semantic web and ontological issues related to the design and implementation of high performance e-learning systems enabled by advanced semantic web and ontological engineering (de Pablos & Lytras, 2013; Vargas-Vera & Lytras, 2008). Mobile learning technologies support the transmission and delivery of rich multimedia content; consequently, mobile learning allows students to access academic online resources from any location, at any given time, thanks to the use of wireless and mobile devices (Pieri & Diamantini, 2009; Traxler, 2007). This social aspect is central to the way people learn in the mobile learning community and the adoption of new technologies often signals the decline of old models of interaction. In this context, some authors combine theoretical methods in social learning analytics—such as social learning network analysis and social learning content analysis—in studying the impact of social multimedia systems on cyberlearners (Zhuhadar, Yang, & Lytras, 2013). The concept of ambient networks, related to a cooperative mobile networking for the wireless world, is introduced in Niebert, Schieder, Zander, and Hancock (2007); on the other hand, Wittenburg and Schiller (2012) discusses the problem of service placement, which is a complement of ambient networks. 3. Technological advances: repositories and tools The role played by computing for human learning becomes of singular importance when collaborative and mobile learning are applied in postgraduate level courses. Thus, several technological advances which have influenced educational environments, namely repositories and tools, are briefly described in this section. 3.1. Repositories The availability of public data sets repositories represents an important set of advantages for scientific research groups worlwide, since this kind of resources enables and facilitates scientific research activities, as well as the creation and design of mathematical models for data analysis. According to Robles, GonzalezBarahona, Izquierdo-Cortazar, and Herraiz (2011), it is clear that research groups worldwide have already taken benefit from the availability of such a rich amount of data sources in the last years. Nonetheless, the access, retrieval and fact extraction is by no means a simple task and many considerations and details have to be taken into account to successfully retrieve and mine the data sources. The UCI Machine Learning Repository (http://archive.ics.uci.edu/ml/about.html) is one of the most famous, and useful, public data set repositories; it is a collection of databases, domain theories, and data generators that are used by the machine learning community for the empirical analysis of machine learning algorithms. There exist public data set repositories for almost every scientific discipline. For instance, the Protein Data Bank (PDB) is a

repository for the 3-D structural data of large biological molecules, such as proteins and nucleic acids (www.rcsb.org/pdb/). The torrent of data streaming from large, government-funded genome sequencing centers has driven the development of excellent open platforms, such as the Genome Analysis Toolkit and Burrows-Wheeler Aligner (Harland & Foster, 2012). Recently, the concept of Enhanced Publication (EP) has appeared. This concept is closely related to the manner in which information is presented in public data sets repositories (Hogenaar & Hoogerwerf, 2009). Walsh (2001) describes how the NASA invests significant resources in collecting data sets that serve the science community, but those data sets can only be judged ‘‘successful’’ if scientists use them effectively. 3.2. Tools Among the computational tools currently available, open tools are very relevant, thanks to the advantages they offer to researchers and practitioners alike. Kelly, Wilson, and Metcalfe (2007) claim that we need a process for adopting open approaches which is based on a desire to exploit the potential benefits of open standards, open source, and open access. According to Brocco and Frapolli (2011) and Koranne (2011), there is a wide variety of open computational tools, which are applied intensely and consistently in educative fields. This is particularly true in mobile learning environments, when collaborative learning is applied. Moreover, as Janert (2011) explains extensively, it is viable, practical, and inexpensive to do data analysis tasks with open source tools. Following this idea but for a different context, Moore et al. (2008) present appropriate methods to use open computational tools for storage and management of quantitative image data. Below, several computational tools used by the Alpha–Beta Research Group—when coupling collaborative and mobile learning in the context of postgraduate level courses—are described. GNU Octave is a high-level interpreted language, primarily intended for numerical computations. It provides capabilities for the numerical solution of linear and nonlinear problems, and for performing other numerical experiments. It also provides extensive graphics capabilities for data visualization and manipulation. Octave is normally used through its interactive command line interface, but it can also be used to write non-interactive programs (Quarteroni & Saleri, 2006). Another useful computational tool is the use of wikis. In this context, a wiki can be defined as a collaborative web space where anyone can add content and anyone can edit content that has already been published (Richardson, 2010). Wikis offer a shared online environment where students can actively participate in the collaborative creation and integration of knowledge, and thus they may be used to encourage the flourishing of dynamic online learning communities, where students meet to achieve a common goal. Thus, the members of such a Wiki community use this joint space to write, discuss, comment, edit, reflect, and evaluate their ideas and work, aiming at completing a shared outcome (West & West, 2009). Brocco and Frapolli (2011) claim that the most well-known source of open knowledge on the Internet is Wikipedia, which was created in 2001 by Jimmy Wales and Larry Sanger. Wikipedia aims at enabling worldwide free access to knowledge, promoting collaborative authoring and reviewing. Huettner, Brown, and James-Tanny (2007) provide valuable information for beginning the use of Wikis. One of the most important and useful tools is Weka, which is currently used extensively by the Alpha–Beta Research Group. According to Hall et al. (2009), Weka is a collection of machine learning algorithms for data mining tasks, including data pre-processing, classification, regression, clustering, association rules, and visualization. The algorithms included can be applied directly to a


dataset or called from a piece of Java code. Weka is also well-suited for developing new machine learning schemes (Witten & Frank, 2005). Weka is made up by four main applications (Explorer, Experimenter, Knowledge Flow, and Simple CLI), which help the researcher to test different classification, clustering, or regression algorithms on any data set. By using the Explorer interface, the user is able to load a specific data set and apply to it a wide variety of artificial intelligence algorithms included in the platform, in order to tackle some problem from any field of human knowledge. 4. Pedagogical experiences in the Alpha–Beta Research Group In this section, the pedagogical experiences lived by the authors in the Alpha–Beta Research Group when coupling collaborative and mobile learning in the context of postgraduate level courses, are presented. The activities related to these pedagogical experiences and their results are immersed in some fields of computer sciences, namely: associative memories, unconventional computing, pattern recognition, metaheuristics, and mathematical morphology. These models along with neural networks and their applications have been present in the scientific activities of the Alpha–Beta Research Group, and in several occasions our research activities are inspired by the accomplishments obtained by other research groups in topics as relevant as the Hopfield neural networks, to cite just one example (Sammouda, Adgaba, Touir, & Al-Ghamdi, 2014). The kernel of the implemented general working strategy is collaborative learning in a modern social networking environment. This strategy includes the following steps: First, each research team, made up by professors and students working in a collaborative learning environment, use mobile learning tools along with modern social networking to choose the topic or problem to work on. Then, the team members use mobile learning tools in a collaborative fashion to access a public data set repository in order to acquire appropriate data sets. Later, an original computer sciences model based on several of these disciplines: associative memories, unconventional computing, pattern recognition, neural networks, metaheuristics, and mathematical morphology, is implemented in order to perform pattern recognition tasks. Finally, the model is tested and a performance comparative study is done with the aid of open tools like Weka, by comparing the results obtained against those given by classic and state of the art methods, over the same data set, which is taken from a public data set repository such as The UCI Machine Learning Repository. 4.1. Medical environments A lot of work has been done by members of the Alpha–Beta Research Group when coupling collaborative and mobile learning in the medical environments. In López-Yáñez, Flores-Carapia, Yáñez-Márquez, and Camacho-Nieto (2011) an automatic pattern classification system, whose goal is to detect the presence or absence of fractures in cranial radiographic images, was presented. The basis for the proposal is an original coding technique, coupled with an emerging model: the Gamma classifier. The results obtained were competitive, reaching 94.23% of correct classification. Regarding the biomolecules processing field, a model based on Alpha–Beta associative memory and the Needleman-Wunsch algorithm was developed and presented, in Román Godínez, Garibay Orijel, and Yáñez-Márquez (2011). The objective of this model is to correctly recall altered version of learning patterns with one

941

or more of the following modifications: insertions, deletions, and mutations, very common alterations in DNA and amino acid sequences. To test the performance of the algorithm on bioinformatics and biomedical applications, the model presented here was tested using the genome of the Variovorax paradoxus organism obtained from the NCBI repository. A new model called Associative Memory based Classifier (AMBC) was presented in Aldape-Pérez, Yáñez-Márquez, Camacho-Nieto, and Argüelles-Cruz (2012a, 2012b). The task to cope was medical diagnosis, and a novel approach to perform pattern classification tasks was presented. Throughout the experimental phase, the proposed algorithm was applied in the diagnosis of seven different problems in the medical field (Haberman survival, liver disorders, acute inflammations, Pima Indians diabetes, breast cancer, heart disease, and hepatitis disease). The performance of the proposed model is validated by comparing classification accuracy of AMBC against the performance achieved by the best twenty well known algorithms, which are included in the open tool Weka. Experimental results have shown that AMBC achieved the best classification accuracy averaged over all datasets. The experimental results indicate that no particular method surpasses all other algorithms in all sorts of problems. However, it is noteworthy that the proposed model, AMBC, achieved the best performance in three of the seven pattern classification problems in the medical field, using a 50-50 trainingtest split; in three of the seven pattern classification problems in the medical field, using a 70-30 training-test split; and in four of the seven pattern classification problems in the medical field, using 10 fold cross-validation. Classification in medical diagnosis task was studied in AldapePérez et al. (2012a, 2012b); in this paper, an automatic hepatitis diagnosis system based on associative memories is presented. Hepatitis disease dataset, taken from UCI machine learning repository, was used as medical dataset. Classification accuracy of the proposed approach is 82.67% and it was assessed using stratified 10 fold cross-validation. A different approach was considered in Aldape-Pérez, YáñezMárquez, Camacho-Nieto, and Ferreira-Santiago (2013), where the authors show how the associative memory paradigm and parallel computing can be used to perform feature selection tasks. This approach uses associative memories in order to get a mask value which represents a subset of features which clearly identifies irrelevant or redundant information for classification purposes. The performance of the proposed associative memory algorithm is validated by comparing classification accuracy of the suggested model against the performance achieved by other well-known algorithms when applied to known medical datasets. Recently, in Uriarte-Arcia, López-Yáñez, and Yáñez-Márquez (2014) a novel method for the task of pattern classification is presented. The proposed method combines a hybrid associative classifier (CHAT), a coding technique for output patterns called one-hot vector and majority voting during the classification step. The method is termed as CHAT One-Hot Majority (CHAT-OHM). The performance of the method is validated by comparing the accuracy of CHAT-OHM with other well-known classification algorithms, using four datasets related to the medical field. 4.2. Pollutants During the last two decades, several methods and techniques taken from the area of Pattern Recognition have been employed on the treatment of data concerning pollution and environmental protection. In López-Yáñez, Yáñez-Márquez, Camacho-Nieto, and Argüelles-Cruz (2011), the authors present the results of applying the Gamma classifier to the prediction of future values for air contaminants concentration, obtaining competitive results (RMSE of 0.556382 ppm for carbon monoxide).

942


Following with this topic, in López-Yáñez, Argüelles-Cruz, Camacho-Nieto, and Yáñez-Márquez (2011) the task was the prediction of future air pollutants concentration in Mexico City. The data was taken from the RAMA (Automatic Atmospheric Monitoring Network, Red Automática de Monitoreo Atmosférico in Spanish) database of the SIMAT (Atmospheric Monitoring System, Sistema de Monitoreo Atmosférico, in Spanish) public repository; the model used was an adaptation of the Gamma classifier to time series prediction, which offered competitive performance. The experimental results shown here predict the contaminant of interest, CO in this case; however, given that the concentration value of a contaminant is used to compute its corresponding IMECA, such predicted concentration of CO is of great importance for the prediction of the IMECA value. The performance results obtained indicate that the gamma Classifier exhibits a good performance for CO concentration, with a RMSE of 0.5564 ppm and bias of 4.6. In Sepúlveda-Lima, Yáñez-Márquez, López-Yáñez, and Camacho-Nieto (2012) the members of the Alpha–Beta Research Group ventured into a relevant research area, related to information security. In this instance, the authors considered the existence of risks and treaths to the integrity of the information that flows constantly from one community to another. Thus, the authors present a novel solution to the secure exchange of environmental pollution data, which is based on cryptographic protocols and algorithms. This solution was heavily inspired by two sources; on one hand, the seminal ideas included in the doctoral dissertation of one of the authors, who is a member of the Alpha–Beta Research Group. On the other hand, the concepts conveyed by Lytras in a document that has already become a classic in the field of sustainable development research (Lytras, 2010): an editorial pertaining to a special edition about Information Systems Research for a Sustainable Knowledge Society, published in 2010.

In the field of computer science an area of great relevance is software engineering, especially the topics related to predicting of the behavior of software development teams, regarding the effort invested in project development or prospective development duration. The Alpha–Beta Research Group has successfully applied its foremost development, the Gamma classifier, to development effort prediction of software projects (López-Martin, López-Yáñez, & Yáñez-Márquez, 2012). Currently we are in the process of diving into large scale projects via identification and quantitative analysis of project success factors, inspired by (Shahzad & Said, 2014).

In (Barr, 2002), Interprofessional Education—a concept coined by the World Health Organization—is used, in order to develop the ability to collaboratively share knowledge and skills in postgraduate courses in medical education. Unlike our work, this author puts emphasis on a unique resource as the strength of the work: problem-based learning (PBL). Macdonald (2003) explore the role of assessment with respect to the processes and products of online collaborative study, choosing as case studies two UK open University courses which have used a variety of models of online collaborative assessment. As can be seen, the goal of this work is to evaluate the processes and products of online collaborative study, not to apply methods of collaborative learning. Among the works described in this section, the one published by Luckin, Brewster, Pearce, Du Bolay, and Siddons-Corby (2005) is the closest to our proposal. The evident difference lies in that the authors of that work do not develop computer science applications. Instead, they focus on a course called Interactive Learning Environments, which is offered to postgraduate students of the University of Sussex, and whose aim is to offer informatics students a mix of theoretical grounding, case study examples and hands-on experience with developing technologies. The authors of Coutinho and Bottentuit Junior (2007) describe a collaborative learning experience with postgraduate students attending a master degree course in Educational Technology at the University of Minho, Braga, Portugal. The results obtained by them are quite limited compared to those of our proposal, given that they use only one wiki, and do not develop computer science applications for actual problems. Shahzad, Valcke, and Bahoo (2012) analyze the teachers perceptions about the adoption of collaborative learning in postgraduate classes of Islamia University of Bahawalpur. This study is limited to identifying problems faced by the teachers when adopting collaborative learning and instruction, as well as providing several recommendations for postgraduate collaborative learning to be successful. The more recent work which is marginally related to this proposal is the one presented in Escudero, León, Perry, Olmos, and Jorge-Botana (2013), whose authors analyzed a time effect variable on the performance of collaborative versus individual tasks with postgraduate students. Their results suggest some implications for when to incorporate collaborative learning tasks in virtual learning environments. However, they do not apply any methods of collaborative learning nor tackle actual problems with computer science algorithms, unlike our proposal.

4.4. Concept lattices

6. Conclusions and future work

In Acevedo, Yáñez-Márquez, and Acevedo (2010) Alpha–Beta bidirectional associative memories are implemented for storing concept lattices. First, the Lindig algorithm is used to build a concept lattice pertaining to a particular context; then, this structure is stored into an associative memory in a similar manner to how human beings do: by associating patterns. Bidirectionality and perfect correct of the Alpha–Beta associative model make it a great tool to store a concept lattice. In the learning phase, objects and attributes obtained from the Lindig algorithm are associated by Alpha–Beta bidirectional associative memory. In the recalling phase, the associative model allows the retrieval of objects from attributes or vice versa.

In this paper, the members of the Alpha–Beta Research Group have presented some interesting and relevant pedagogical experiences, acquired by the authors in the context of postgraduate level courses, when coupling collaborative and mobile learning. The remarkable advancements experienced by collaborative and mobile learning in educational environments is undoubtedly due to the use of computing for human learning. This circumstance is a positive consequence of living in a world which is already immersed in the era of social and mobile networks. The use of modern educational technologies, as computational tools and repositories, has greatly enhanced the learning experiences of all students involved. The collaborative learning shown by the postgraduate level students has allowed the enhancing of development of original computational models. Among others applications, members of the Alpha–Beta Research Group (both students and researchers) have tackled problems pertaining to medical environments, pollution, and concept lattices. Students employed the tools and repositories to improve

4.3. Software engineering

5. Related work Several researchers have developed works with research approaches similar or related to ours. Below are described some of the most notable such works, comparing them to our approach.


their teaching-learning processes, immersed in collaborative and mobile learning. As a future work, the authors intend to continue fostering the collaborative and mobile learning among the students which are members of the Alpha–Beta Research Group. For that, we will explore the use of social networks in the postgraduate level courses. Acknowledgements The authors would like to thank the Instituto Politécnico Nacional (Secretaría Académica, COFAA, SIP, CIC, and CIDETEC), the CONACYT and SNI, for their economical support to develop this work. References Acevedo, M. E., Yáñez-Márquez, C., & Acevedo, M. A. (2010). Associative models for storing and retrieving concept lattices. Mathematical Problems in Engineering, 356029. 27p. Aldape-Pérez, M., Yáñez-Márquez, C., Camacho-Nieto, O., & Argüelles-Cruz, A. J. (2012a). An associative memory approach to medical decision support systems. Computer Methods and Programs in Biomedicine, 103(3), 287–307. Aldape-Pérez, M., Yáñez-Márquez, C., Camacho-Nieto, O., & Argüelles-Cruz, A. J. (2012b). A new tool for engineering education: Hepatitis diagnosis using associative memories. International Journal of Engineering Education, 28(6), 1399–1405. Aldape-Pérez, M., Yáñez-Márquez, C., Camacho-Nieto, O., & Ferreira-Santiago, A. (2013). Feature selection using associative memory paradigm and parallel computing. Computación y Sistemas, 17(1), 41–52. Alexander, B. (2004). Going nomadic: Mobile learning in higher education. EDUCAUSE Review, 39(5), 28–35. Barr, H. (2002). Interprofessional education. Educational Strategies, 24, 187–192. Benson, V., Morgan, S., & Tennakoon, H. (2012). A framework for knowledge management in higher education using social networking. International Journal of Knowledge Society Research, 3(2), 44–54. Bottino, R. M. (2012). Framing technology enhanced learning environments: Some perspectives and notions. International Journal of Knowledge Society Research, 3(1), 67–81. Brocco, A., & Frapolli, F. (2011). Open source in higher education: Case study computer science at the University of Fribourg. Diploma of Advanced Studies, Centre de Didactique Universitaire, University of Fribourg, Switzerland. Coutinho, C. P., & Bottentuit Junior, J. B. (2007). Collaborative learning using wiki: A pilot study with master students in educational technology in Portugal. In Proceedings of EDMEDIA 2007 world conference on educational multimedia, hypermedia & telecommunications (pp. 1786–1791). Canadá: Vancouver. de Pablos, P. O., & Lytras, M. D. (2013). Editorial: Semantic Web and social networks for E-learning. Journal of Web Engineering, 12(5), 361–362. Dillenbourg, P. (1999). What do you mean by collaborative learning? In P. Dillenbourg (Ed.), Collaborative-learning: Cognitive and computational approaches (pp. 1–19). Oxford: Elsevier. Escudero, I., León, J. A., Perry, D., Olmos, R., & Jorge-Botana, G. (2013). Collaborative versus individual learning experiences in virtual education: The effects of a time variable. Procedia-Social and Behavioral Sciences, 83, 367–370. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009). The Weka data mining software: An update. SIGKDD Explorations, 11(1), 10–18. Harland, L., & Foster, M. (2012). Open source software in life science research: Practical solutions to common challenges in the pharmaceutical industry and beyond. Cambridge: Woodhead Publishing Limited. Hogenaar, A., & Hoogerwerf, M. (2009). Sample datasets and demonstrator. In M. Vernooy-Gerritsen (Ed.), Enhanced publications-linking publications and research data in digital repositories (pp. 133–156). Amsterdam: Amsterdam University Press. Huettner, B., Brown, M. K., & James-Tanny, C. (2007). Managing virtual teams: Getting the most from wikis, blogs, and other collaborative tools. Texas: Wordware Publishing Inc. Janert, P. K. (2011). Data analysis with open source tools. Sebastopol: O’Reilly Media Inc. Kearney, M., Schuck, S., Burden, K., & Aubusson, P. (2012). Viewing mobile learning from a pedagogical perspective. Research in Learning Technology, 20, 14406. Kelly, B., Wilson, S., & Metcalfe, R. (2007). Openness in higher education: Open source, open standards, open access. In L. Chan, & B. Martens (Eds.), 11th International conference on electronic publishing. Openness in digital publishing: Awareness, discovery and access (pp. 161–174). Vienna. Koranne, S. (2011). Handbook of open source tools. New York: Springer + BusinessMedia. Kukulska-Hulme, A. (2010). Mobile learning as a catalyst for change. Open Learning: The Journal of Open and Distance Learning, 25(3), 181–185. Lehtinen, E., Hakkarainen, K., Lipponen, L., Rahikainen, M., & Muukkonen, H. (1999). Computer supported collaborative learning: A review. The JHGI Giesbers reports on education, 10.

943

López-Martin, C., López-Yáñez, I., & Yáñez-Márquez, C. (2012). Application of Gamma classifier to development effort prediction of software projects. Applied Mathematics & Information Sciences, 6(3), 411–418. López-Yáñez, I., Argüelles-Cruz, A. J., Camacho-Nieto, O., & Yáñez-Márquez, C. (2011). Pollutants time series prediction using the Gamma classifier. International Journal of Computational Intelligence Systems, 4(4), 680–711. López-Yáñez, I., Flores-Carapia, R., Yáñez-Márquez, C., & Camacho-Nieto, O. (2011). Automatic detection of cranial fractures in radiological images using a pattern classifier. Revista Facultad de Ingeniería, 61, 29–40. López-Yáñez, I., Yáñez-Márquez, C., Camacho-Nieto, O., & Argüelles-Cruz, A. J. (2011). Prediction of air contaminant concentration based on an associative pattern classifier. Revista Facultad de Ingeniería, 60, 20–30. Luckin, R., Brewster, D., Pearce, D., Du Bolay, B., & Siddons-Corby, R. (2005). Whether it’s m-learning or e-learning, it must be ME learning. In A. Kukulska-Hulme & J. Traxler (Eds.), Mobile learning: A handbook for educators and trainers (pp. 116–124). New York: Taylor & Francis Inc. Lytras, M. D. (2010). From the special issue editor: Information systems research for a sustainable knowledge society. Information Systems Management, 27(3), 196–197. Lytras, M. D., & de Pablos, P. O. (2009). Social Web evolution: Integrating semantic applications and Web 2.0 technologies. New York: IGI Global Information Science Reference. Lytras, M. D., & de Pablos, P. O. (2011). Software technologies in knowledge society. Journal of Universal Computer Science, 17(9), 1219–1221. Lytras, M. D., & Kurilovas, E. (2014). Editorial: Special issue on information and communication technologies for human capital development. Computers in Human Behavior, 30, 361. Macdonald, J. (2003). Assessing online collaborative learning: Process and product. Computers & Education, 40, 377–391. Moore, J., Allan, C., Burel, J. M., Loranger, B., MacDonald, D., Monk, J., et al. (2008). Open tools for storage and management of quantitative image data. Methods Cell Biology, 85, 555–570. Moreno-Moreno, P., & Yáñez-Márquez, C. (2008). The new informatics technologies in education debate. In M. D. Lytras et al. (Eds.), Emerging technologies and information systems for the knowledge society (pp. 291–296). Berlin: SpringerVerlag. Niebert, N., Schieder, A., Zander, J., & Hancock, R. (2007). Ambient networks: Cooperative mobile networking for the wireless world. Chichester: John Wiley & Sons Ltd. Pieri, M., & Diamantini, D. (2009). From E-learning to mobile learning: New opportunities. In M. Ally (Ed.), Mobile learning-transforming the delivery of education and training (pp. 183–194). Edmonton: AU Press. Quarteroni, A., & Saleri, F. (2006). Scientific computing with MATLAB and octave. Berlin: Springer-Verlag. Richardson, W. (2010). Blogs, wikis, podcasts, and other powerful web tools for classrooms. London: SAGE Ltd. Roberts, T. S. (2005). Computer-supported collaborative learning in higher education: An introduction. In T. S. Roberts (Ed.), Computer-supported collaborative learning in higher education (pp. 1–18). London: Idea Group Inc. Robles, G., Gonzalez-Barahona, J. M., Izquierdo-Cortazar, D., & Herraiz, I. (2011). Tools and datasets for mining libre software repositories. In K. Stefan (Ed.), Multi-disciplinary advancement in open source software and processes (pp. 24–42). Hershey: IGI Global. Román Godínez, I., Garibay Orijel, C., & Yáñez-Márquez, C. (2011). A identification of functional sequences using associative memories. Revista Mexicana de Ingeniería Biomédica, 32(2), 48–57. Sammouda, R., Adgaba, N., Touir, A., & Al-Ghamdi, A. (2014). Agriculture satellite image segmentation using a modified artificial Hopfield neural network. Computers in Human Behavior, 30, 436–441. Sepúlveda-Lima, R., Yáñez-Márquez, C., López-Yáñez, I., & Camacho-Nieto, O. (2012). A novel solution to the secure exchange of environmental engineering education data. International Journal of Engineering Education, 28(6), 1380–1387. Shahzad, B., & Said, A. M. (2014). Identification and quantitative analysis of project success factors for large scale projects. International Journal of Knowledge Society Research, 5(1), 83–95. Shahzad, A., Valcke, M., & Bahoo, R. (2012). A study to analyze the teacher’s perceptions about the adoption of collaborative learning in post-graduate classes of IUB. Procedia-Social and Behavioral Sciences, 46, 3056–3059. Sharples, M., Taylor, J., & Vavoula, G. (2005). Towards a theory of mobile learning. In H. van der Merwe & T. Brown (Eds.), Mobile technology: The future of learning in your hands (pp. 58–64). South Africa: Cape Town. Traxler, J. (2007). Defining, discussing and evaluating mobile learning. International Review on Research in Open and Distance Learning (IRRODL), 8(2), 1–12. Uriarte-Arcia, A. V., López-Yáñez, I., & Yáñez-Márquez, C. (2014). One-hot vector hybrid associative classifier for medical data classification. PLoS One, 9(4), e95715. Vargas-Vera, M., & Lytras, M. D. (2008). Exploiting semantic web and ontologies for personalised learning services: Towards semantic web-enabled learning portals for real learning experiences. International Journal of Knowledge and Learning, 4(1), 1–17. Vossen, G., Lytras, M. D., & Koudas, N. (2007). Editorial: Revisiting the (machine) semantic web: The missing layers for the human semantic web. IEEE Transactions on Knowledge and Data Engineering, 19(2), 145–148. Walsh (Chair Committee), J. (2001). Enhancing NASA’s contributions to polar science – A review of polar geophysical data sets. Washington: National Academy Press.

944


Webster, L., & Murphy, D. (2008). Enhancing learning through technology: Challenges and responses. In R. Kwan, R. Fox, F. T. Chan, & P. Tsang (Eds.), Enhancing learning through technology: Research on emerging technologies and pedagogies (pp. 1–16). Singapore: World Scientific. West, J. A., & West, M. L. (2009). Using wikis for online collaboration. San Francisco: Jossey-Bass. Witten, I. H., & Frank, E. (2005). Data mining: Practical machine learning tools and techniques. Amsterdam: Elsevier. Wittenburg, G., & Schiller, J. (2012). Service placement in Ad Hoc networks. London: Springer.

Yáñez-Márquez, C., Aldape-Pérez, M., López-Yáñez, I., & Camacho-Nieto, O. (2014). Emerging computational tools: Impact on engineering education and computer science learning. International Journal of Engineering Education, 30(3), 533–542. Zhuhadar, L., Yang, R., & Lytras, M. D. (2013). The impact of social multimedia systems on cyberlearners. Computers in Human Behavior, 29(2), 378–385. Zurita, G., & Nussbaum, M. (2004). Computer supported collaborative learning using wirelessly interconnected handheld computers. Computers & Education, 42(3), 289–314.