Skip to end of metadata
Go to start of metadata

Pedagogical Agents

The idea behind pedagogical agents is the creation of embedded AI operating in the background of the Smart Space. These agents can monitor the interactions of students and make suggestions, help, track and report back to the teacher.

Need to breakdown notes and come up with types of pedagogical agents and how they would work...

Tutor agents (Jafari, 2002)

  • Send overdue notices to the students for assignments
  • The agent could provide background info on a student, when reporting problems, etc.

Teaching Assistant Agents (Jafari, 2002)

  • Assists students with specific learning needs
  • Could be a "smart search engine"
  • Could "learn" through repeated use and feedback
  • It is assumed that the Digital Tutor has access to students' learning profiles. Accessing student profiles and knowing students' strengths and weaknesses on a learning objective empowers the Digital Tutor to provide more useful resources. (p. 31)
  • System could alert students when group members or other students who might be helpers (scaffolding helpers) log into the system

Secretary Agents (Jafari, 2002)

  • Running calendar and event co-ordination
  • Communication routing and organizing
  • Connecting relevant team members, group mails, chats

Lesson Planning/Instruction Agent (Gregg, 2007)

  • Agents can be used to perform information gathering and sophisticated reasoning necessary to determine appropriate learning sequences (Woolf and Eliot, 2005; Cassin et al., 2003, Sicilia, 2006).
  • Lesson planning agents can be used to assist with the design of the course structure as well as with the selection of appropriate learning materials (p.4)
  • dynamically generate recommended instructional resources and schedules, which can be customized for individual learners.(p.5)
  • decomposes complex topics into simpler subtopics to facilitate the ordering of the materials.(p.6)

Research Location Agent (Gregg, 2007)

With hundreds of thousands of educational resources available on the web, anyone assembling e-learning materials requires assistance to locate appropriate resources online (Gasevic and Hatala, 2006; Woolf and Eliot, 2005). Agents can facilitate location of a wide variety of learning materials, including those that support active learning. (p. 3&4)

  • used to identify additional resources for the specific topic (p.5)
  • Resource discovery can occur in two modes in e-learning environments. The first occurs when learners explore the digital environment on their own to assemble learning materials based on a self-perceived learning need, and the second occurs when domain experts or instructors assemble the reusable learning objects necessary to support a course or learning module.(p.6)
  • can utilize semantic web metadata to help locate and classify new learning materials as well as to monitor existing resources to determine if they have been changed, moved, or eliminated (p.6)

    Needs:

  • Querying
  • Indexing
  • Evaluation

Personalization Agent (Gregg, 2007)

  • Used to create a personalized learning model and pathway tailored to individual learner knowledge and personality traits (p.8)
  • Should be able to select learning materials and optimize schedules for individual learners based on cognitive style, personal preferences, and accessibility needs in addition to prior knowledge and desired knowledge. (p.8)

Collaboration agent (Gregg, 2007)

  • Tools to support socialization between learners and their instructors, community building tools to support the process of building cohesion in a group, and discussion supporting tools (p.8)
  • Suggesting collaboration where appropriate
  • Can monitor the e-learning environment and suggest synchronous "chat" between learners working on similar problems at the same time (p.8)
  • Can also point learners to appropriate discussion threads throughout the learning process (p.8)
  • Can also identify learners that are having difficulty with a particular topic and facilitate their interaction with the instructor, before they become too lost or spend too much time misunderstanding a particular topic (p.8)
  • If a collaboration agent observes too much homogeneity among the group members, it can modify some conditions in order to activate collaboration.

Challenges

While proprietary semantics can lead to effective search on the local repository, the lack of semantic alignment with the outside world reduces usability.(Simon et al. 2006)

Two major obstacles could inhibit the collection, analysis, and use of learning data in an educational institution. First, the technology and the software engine necessary for collection and analysis of learning data do not yet exist. Second, collecting and using learning data could create legal challenges for educational institutions.(Jafari, 2002)

Numerous studies show collaboration is more difficult in e-learning environments. These studies cite such components as physical separation, reduced sense of community, disconnectedness, isolation, distraction, and lack of personal attention as contributors to lack of success in various virtual programs (Kerka, 1996; Besser and Donahue, 1996; Twigg, 1997; Stonebraker and Hazeltine, 2004)

Many of these factors have already been highlighted in our own scenarios on the encore wiki

Although these papers highlight several problems with collaboration and community building I think many of these can be overcome in S3 because this is not 'true' distance learning which is the focus of many of these papers

rough notes

  • No labels