Name
Abstract | ||
|---|---|---|
To successfully interact with users in providing useful information, intelligent user interfaces need a mech- anism for recognizing, characterizing, and predicting user actions. In particular, it is our interest to develop the mechanism for recognizing and predicting simple user intentions, i.e., an activity involves in using partic- ular resources. Much work to date in adaptive user inter- faces has resulted in ad-hoc approaches such as simply capturing user preferences at a shallow level ignoring the more difficult problem of capturing the user inten- tion. We frame the modeling task of user interface sys- tems in terms of learning user patterns of using partic- ular resources by understanding temporal information of activity, user intentions, and abstraction of user be- havior. Our approach learns the individual user models through time-series action analysis and abstraction. Af- ter capturing the dynamics of user behavior into reg- ularities of user behavior(patterns), probabilistic user models are constructed to facilitate the predictions of resource usage with a sequence of currently observed actions in the Unix domain. |
Year | Venue | Keywords |
|---|---|---|
2001 | FLAIRS Conference | predicting user behavior,particular resource use,user interface,time series,user model |
Field | DocType | ISBN |
User experience design,Computer science,Human–computer interaction,User modeling,Computer user satisfaction,User interface design,User interface,Natural user interface,User requirements document,User journey | Conference | 1-57735-133-9 |
Citations | PageRank | References |
1 | 0.36 | 5 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jung Jin Lee | 1 | 35 | 10.24 |
| Robert McCartney | 2 | 31 | 5.27 |
| Eugene Santos Jr. | 3 | 325 | 44.65 |