Rater cognitive processes in integrated writing tasks: from the perspective of problem-solving

Abstract It is widely believed that raters’ cognition is an important aspect of writing assessment, as it has both logical and temporal priority over scores. Based on a critical review of previous research in this area, it is found that raters’ cognition can be boiled to two fundamental issues: building text images and strategies for articulating scores. Compared to the scoring contexts of previous research, the TEM 8 integrated writing task scoring scale has unique features. It is urgent to know how raters build text images and how they articulate scores for text images in the specific context of rating TEM8 compositions. In order to answer these questions, the present study conducted qualitative research by considering raters as problem solvers in the light of problem-solving theory. Hence, 6 highly experienced raters were asked to verbalize their thoughts simultaneously while rating TEM 8 essays, supplemented by a retrospective interview. Analyzing the collected protocols, we found that with regard to research question 1, the raters went through two stages by setting building text images as isolated nodes and building holistic text images for each dimension as two sub-goals, respectively. In order to achieve the first sub-goal, raters used strategies such as single foci evaluating, diagnosing, and comparing; for the second sub-goal, they mainly used synthesizing and comparing. Regarding the second question, the results showed that they resorted to two groups of strategies: demarcating boundaries between scores within a dimension and discriminating between dimensions, each group consisting of more specific processes. Each of the extracted processes was defined clearly and their relationships were delineated, on the basis of which a new working model of the rating process was finalized. Overall, the present study deepens our understanding of rating processes and provides evidence for the scoring validity of the TEM 8 integrated writing test. It also provides implications for rating practice, such as the need for the distinction between two types of analytical rating scales.