C. Baur, M. Rayner, N. Tsourakis

University of Geneva (SWITZERLAND)
We describe work carried out in the context of a project whose goal is to develop a web-enabled serious game designed to help German-speaking beginner students of English improve their generative and auditory competence. The game, which is currently undergoing a first round of formal user testing, is intended as a self-study adjunct to normal classroom instruction. It was developed in collaboration with a secondary school teacher, with the content taken from a textbook commonly used in German-speaking Switzerland, and offers a short course of 8 interactive lessons using a combined vocabulary of about 450 words.

A lesson is structured as a short prompted dialogue between the student and the machine, where the student is encouraged to use simple language in practical contexts like booking a hotel room, buying clothes, or ordering a meal in a restaurant. At each turn, the system starts by playing a short video file in English (“How may I help you?”), and simultaneously displays a piece of text in German indicating to the student how they should reply (Ich möchte ein Zimmer für 2 Nächte). The student gives a spoken response, which is processed using domain-specific speech recognition technology and either accepted or rejected. Dialogue structure is specified in a simple XML-based script formalism; there are multiple paths through the script, with choices made randomly. The system is gamified using a score-and-badge framework, with four levels of badges, and is available for unrestricted access at

The architecture, lesson content and initial data collection work, have been described in earlier publications (, Although some students appear to enjoy using the system, recorded interactions from our initial tranche of data often show others responding in a bored or irritated tone; since it is unlikely that students will use a self-study tool which they do not find reasonably enjoyable, this indicates a clear problem. In the present paper, we focus on a strategy we have recently developed which is intended to make the dialogues more interesting and engaging.

The central idea is to add further dialogue paths to the scripts, graded by their degree of “cooperativeness”. The core dialogue flow for a lesson, which is followed at the lowest badge levels, is a cooperative interaction; for example, in the Restaurant lesson, the student orders their meal, asks for the bill, and pays. When they reach a higher badge level, more dialogue paths are activated; the waiter may for example bring the wrong food, requiring the student to complain or ask to see the manager. The “uncooperative” paths fulfil a double function. First, they make the game more varied, so that students are less likely to be bored. In addition, the student is given tangible feedback on their linguistic progress: as soon as they are able to negotiate the cooperative version of the exchange well enough to reach the higher badge levels, they start to be confronted with the more demanding uncooperative versions.

The full version of the paper will describe the “uncooperative dialogue” idea in more detail and present results from initial user trials.