Passive Air Cooling System and Solar Water Heater.ppt
recommendations in e-learning environment
1. Recommendations using learners navigational
behaviour in e-learning environment.
V. Saritha
Assistant Professor
e-learning recommendations by v.saritha is licensed under a Creative Commons Attribution-
ShareAlike 4.0 International License.
2. ABSTRACT
Recommender systems can reduces the workload of learners. In Order to improve the
accuracy and quality of recommendations, recommendations based on sequential pattern
mining and attribute-based collaborative filtering (CF) is proposed. In the sequential pattern
based approach, PrefixSpan algorithm are implemented to discover patterns. The proposed
method outperforms the previous recommendation approaches on the classification accuracy
measures and the learner’s real learning preference.
3. Problem Definition
With growth of many online learning systems, a huge amount of e-learning materials have
been generated .Therefore, it is quite difficult to find suitable learning materials based on
learner’s preference. The task of delivering learning material is often framed in terms of a
recommendation task in which a system recommends learning meterial to an active
user.Therefore, recommender systems have been used for e-learning environments to
recommend useful materials to users. These systems address information overload and make
a efficient learning environment for users. The motivation for any recommender system is
to assure an efficient use of available materials.
4. EXISTING SYSTEM
● Content based
● CF
● hybrid
● Traditional recommendation algorithms only use learners’ rating for
recommendation and don’t consider attributes of learners and learning
materials.
● The learners’ preferences will be changing dynamically which are not
managed in existing.
5. PROPOSED APPROACH
Our proposed approach takes into account both users’ possible preferences on learning
items and the sequential patterns hidden in them. The proposed recommendation model
is collaborative filtering.
● Collaborative Filtering methods are based on collecting and analyzing a large
amount of information on users’ behaviors, activities or preferences and predicting
what users will like based on their similarity to other users.
6. ● ¨Given a database of sequences , where each sequence is an ordered list of events,
denoted < e1 e2 … el > ordered by time and each event is a set of items.
● Sequential Pattern Mining can be defined as the process of discovering all
subsequences that appear frequently on a given sequence database and have minimal
support threshold. Minimum support is the number of data sequences that are present
in the pattern.
7. ● Web sequential pattern mining is based on the web access log.
● Firstly , we should preprocess the web access log and then perform
the sequential pattern mining algorithm like prefix span.
● No candidate generation
● It uses the Divide and conquer search methodology.
Proposed Methodology
10. CONCLUSION
The recommendation algorithm, which combines CF and SPM together will be
efficient from the existing approaches. Several adaptations are made for the proposed
approach to be suitable for the e-learning environment. We also apply the proposed
approach to the already existing data to justify the results.