Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Optimizing search results for human learning goals
Syed R., Collins-Thompson K. Information Retrieval20 (5):506-523,2017.Type:Article
Date Reviewed: Feb 7 2018

For many students, web search is an important part of the learning process. However, existing search engines are optimized so as to achieve the largest average customer satisfaction among different categories of customers. Because of this, search results are not always very helpful for students who are learning the corresponding topic. It is therefore desirable to come up with a special search engine optimized for students’ use. To achieve this goal, the authors supplemented the title of the studied topic with a list of appropriate keywords. Each keyword is assigned a weight--based, for example, on how frequently the keyword is used in corresponding textbooks or other educational material in comparison with language in general.

The authors then performed several Google searches, with the original title supplemented by each of these keywords. From the few top results of each of these searches, they select the links that, crudely speaking, provide the largest number of occurrences of the keywords--of course, taking into account the weights of different keywords, the degrees of the links’ relevance, and the need to avoid duplication. Several versions of the resulting algorithm have been tested on real-life students, and the empirically best version is selected. For some topics, the resulting optimized algorithm led to an impressive three-to-four-times speed-up in learning.

The remaining open problems include gauging the role of pictures in learning, taking into account the difficulty level of different texts, and extending this approach to more complex learning tasks. A very interesting paper, it can be recommended to researchers and graduate students interested in this topic.

Reviewer:  V. Kreinovich Review #: CR145835 (1805-0257)
Bookmark and Share
  Featured Reviewer  
 
Learning (I.2.6 )
 
 
Retrieval Models (H.3.3 ... )
 
 
Optimization (G.1.6 )
 
Would you recommend this review?
yes
no
Other reviews under "Learning": Date
Learning in parallel networks: simulating learning in a probabilistic system
Hinton G. (ed) BYTE 10(4): 265-273, 1985. Type: Article
Nov 1 1985
Macro-operators: a weak method for learning
Korf R. Artificial Intelligence 26(1): 35-77, 1985. Type: Article
Feb 1 1986
Inferring (mal) rules from pupils’ protocols
Sleeman D.  Progress in artificial intelligence (, Orsay, France,391985. Type: Proceedings
Dec 1 1985
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy