Markov Chain Models for Menu Item Prediction
| Autor: | Tao Lin, Tiantian Xie, Ningjiu Tang, Yi Mou |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Structure (mathematical logic)
Markov chain Computer science business.industry Machine learning computer.software_genre Field (computer science) Human-Computer Interaction Task (computing) Probability summation Genetic algorithm Mental load Artificial intelligence business computer Predictive modelling Simulation Information Systems |
| Zdroj: | International Journal of Technology and Human Interaction. 9:75-94 |
| ISSN: | 1548-3916 1548-3908 |
| DOI: | 10.4018/ijthi.2013100105 |
| Popis: | With the increase in the number of menu items and the menu structure complexity, users have to spend more time in locating menu items when using menu-based interfaces, which tends to result in the decrease of task performance and the increase of mental load. How to reduce the navigation time has been a great challenge in the HCI (human-computer interaction) field. Recently, adaptive menu techniques have been explored in response to the challenge, and menu item prediction plays a crucial role in the techniques. Unfortunately, there still lacks effective prediction models for menu items. This paper explores the potential of three prediction models (i.e., Absolute Distribution Markov Chain, Probability Summation Markov Chain and Weighted Markov Chain based on Genetic Algorithm) in predicting the most possible N (Top-N) menu items based on the users’ historical menu item clicks. And the results show that Weighted Markov Chain based on Genetic Algorithm can obtain the highest prediction accuracy and significantly decrease navigation time by 22.6% when N equals 4 as compared to the static counterpart. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|