However, we should be aware that monitoring is not an end in itself [20][23][24]: in addition to carefully deciding what and when to monitor, the tracking process is further complicated by the issue of appropriate interpretation of the gathered data and correctness of inferences made from that data. Erroneous assumptions about the learner’s input, his language knowledge and skills, may cause wrong action by the system, consequently leading to an inefficient learning process and poor language attainment [14].
C. The Tutoring Model
The tutoring model is made up of rules that define how a system should act during runtime, taken into consideration the data from the learner model [17]. It specifies which pedagogical action should be taken following each user activity. Therefore, this model defines what, when and how to adapt within the system [25]. In order for the adaptive action of a language learning- oriented ITS to be effective, the knowledge from language learning theory (usually First language acquisition (FLA) or Second language acquisition (SLA)) and pedagogical practice should be included as part of this model.
D. The User Interface Model
The interface model was only recently added to the above three, and is concerned with the graphical environment through which educational content is delivered to the learner [2]. In particular, it deals with the representation of instructional material, mostly focusing on multimedia and its advantages for the learner.
E. The Feedback Module
Another important and frequently included element of an ITS for language learning is the feedback module. Language teachers are often engaged in giving feedback to learners concerning their progress, success on a particular task, language areas they need to work on, etc. Similarly, tutoring systems should also be able to adequately respond to a learner activity.
Giving feedback may consist in a straightforward declaration of errors (e.g., The answer you provided is not correct.), request for additional clarification (e.g., What do you mean by…) or restating something in a correct manner [18]. In many ways this entails the usage of NLP techniques so that the computer is able to make sense of the learner’s written or spoken input.
From the point of view of technology, there are three possible approaches to appropriate feedback formation: pattern matching-based approach, statistical-based approach and rule-based approach [26].
III. ISSUES SURROUNDING THE DEVELOPMENT OF ITSS
Designing each of the components of an ITS for language learning requires a careful consideration of the needs of both learners and teachers. In the light of that and based on available reports from literature on specific language-learning ITSs, we point out some of the issues that may arise during the development process, briefly explain them, and, where appropriate, offer some suggestions as to possible solutions.