A large array of evaluation methods have been proposed to identify Website usability problems. In log-based evaluation, information about the performance of users is collected and stored into log files, and used to find problems and deficiencies in Web page designs. Most methods require the programming and modeling of large task models, which are cumbersome processes for evaluators. Also, because much statistical data is collected onto log files, recognizing which Web pages require deeper usability analysis is difficult. This paper suggests a novel quantitative method, called the D-TEO, for locating problematic Web pages. This semiautomated method explores the decomposition of interaction tasks of directed information search into elementary operations, deploying two quantitative usability criteria, search success and search time, to reveal how a user navigates within a web of hypertext.