连贯阅读中文本表征的意识性研究

Consciousness of Text Representation in Coherence-based Reading

采用独立记得-知道范式(IRK)和加工分离范式(PDP)探讨连贯阅读中文本表征的意识性。根据阅读材料中人物特征与其目标行为的关系,创设了一致和恢复一致两种实验条件,实验1使用独立记得-知道范式分析被试两种条件下对再认项目判断为"记得"或"知道"的比例(击中率),实验2使用加工分离范式分析被试在包含、排斥测验中两种条件下的击中率和虚报率。两个实验的结果都发现一致和恢复一致条件在有意识和无意识加工指标上都没有显著差异,说明在连贯阅读中命题表征和情境模型的建构都是无意识的,该结果支持和完善了文本阅读双加工理论。

Long and Prat （2006） found that the construction of a situation model is conscious while the construction of textbase is unconscious through two paradigms（IRK and PDP）. This is inconsistent with the processing theory of bi-mechanism in text-reading, which states that the construction of a situation model is unconscious in coherence-based reading while it is conscious in focus-based reading. We think that the inconsistence is caused by the nature of the experiment material. In this study, two experiments were designed to explore the consciousness of a situation model and textbase in coherence-based reading with both IRK and PDP paradigms. In Experiment 1, 30 university students were asked to read 12 narrative passages with two elaboration versions （consistent and inconsistent）. After reading all of the texts, they received the recognition test. They were instructed to press a key labeled ＂new＂ if they believed the sentence did not appear in one of the texts they had read, otherwise, to press a key labeled ＂old＂. Then they were to decide whether they had a vivid, clear consciousness of the sentence. If so, they were to press a key labeled ＂R＂ （remember）. If they did not have a vivid, dear consciousness of the sentence but still believed the sentence had appeared in one of the texts, they were to press a key labeled ＂K＂ （know）. In Experiment 2, 32 university students were asked to read 12 groups of narrative passages with two elaboration versions （consistent and inconsistent）. Each participant read six blocks of consistent-version texts and six blocks of qualified-version texts, and then received a recognition test after each block. After reading one block, they were given an instruction （inclusion or exclusion）. In the inclusion test, the participants were to respond ＂old＂ if the sentence appeared in either Story A or Story B and to respond ＂new＂ to any new item. In the exclusion test, the participants were to respond ＂old＇＇ only if the sentence appeared in Story B and to respond ＂new＂ if the sentence was from Story A or if the item was new. In these two experiments, the reading time of target sentences in the qualified condition was longer than that in the consistent condition. More importantly, there was no difference between the consistent version and qualified version in the rate of The results showed that both the construction of situation model and textbase was unconscious in coherence-based reading. This research extended and deepened the processing theory of bi-mechanism in text-reading