Please enable JavaScript.
Coggle requires JavaScript to display documents.
Process Tracking Methods (Other Manual methods (Brainstorming: These…
Process Tracking Methods
-
A popular approach among cognitive psychologists who are interested in discovering the expert's train of thought in reaching a conclusion
-
-
Observation
-
-
However, the difficulties involved should not be underestimated
For example, most experts advise several people and may work in several domains simultaneously
Other Manual methods
Discussion with users: Even though users are not experts, they can be quite knowledgeable about some aspects of the problem
They can also indicate areas where they need help. The expert may be unaware of some of the users' needs
Commentaries: With this method, the knowledge engineer asks experts to give a running commentary on what he/she is doing
This method can be supported by videotaping the experts in action or by asking an observer to do the commentary
Brainstorming: These methods can be used to solicit the opinions of multiple experts and can help generate ideas
Electronic brainstorming can also be used, including black boarding which has been implemented as electronic whiteboards
The recently available software for this, such as Microsoft NetMeeting, MSN Messenger etc. are powerful tools for holding remote knowledge acquisition sessions
Prototyping: Working with a prototype of the system is a powerful approach to inducing experts to contribute their knowledge
-
Conceptual graphs and models: Diagrams and other graphical methods can be instrumental in supporting other acquisition methods
A conceptual model can be used to describe how and when the expert's knowledge will come into play as the ES performs its task
-
Critical incident analysis, In this approach, only selected cases are investigated
Usually those that are memorable, difficult or of special interest. Both experts and non-experts may be questioned
Automatic Methods
-
-
In early 1990s, the process was also called machine learning but knowledge discovery and data mining (KDD) is now a more popular term
Why Automatic Methods?
- Good knowledge engineers are highly paid and difficult to find
- Domain experts are usually busy and sometimes uncooperative
As a result, manual and even semiautomatic elicitation methods are slow and expensive
-
Semi Automatic Methods
-
These tools provide an environment in which KE or experts can identify knowledge through an interactive process
e.g. Computer Aided tools: PROTEGE-II, KSM
-