• Most Accessed Pages, using page request frequency.
• Company's Interest Pages, combining a priori rewards the site owner assigns to states with the particular page selection the user traverses. CIP applies a value-determination algorithm to calculate new links' utilities on the basis of the states' rewards and the current state, and the probability of traversing to the link from the current state.
• buy (strong positive feedback)
• browse (weak positive feedback)
• ignore—does not get to an item on the list (no change)
• explicitly skip—bypasses an item even when presented (negative feedback)
• remove (strong negative feedback)
Javed Mostafa is the Victor H. Yngve Associate Professor of Information Science and Associate Professor of Informatics at Indiana University. He is the director of the Laboratory of Applied Informatics Research at Indiana University. His research interest is intelligent interfaces for information retrieval. He has a PhD in information science from the University of Texas at Austin. He is a member of the AAAS, the ACM, ASIST, and the IEEE. Contact him at Indiana Univ., 1320 E 10th St., Bloomington, IN 47405-3907; email@example.com; http://lair.indiana.edu.