中文题名: | 三余阅读APP句式自动测评模块的设计与运用研究 |
姓名: | |
保密级别: | 公开 |
论文语种: | 中文 |
学科代码: | 040104 |
学科专业: | |
学生类型: | 学士 |
学位: | 理学学士 |
学位年度: | 2020 |
学校: | 北京师范大学 |
校区: | |
学院: | |
第一导师姓名: | |
第一导师单位: | |
提交日期: | 2020-06-10 |
答辩日期: | 2020-05-17 |
外文题名: | The design and application of sentence pattern automatic evaluation module in SanYu Reading APP |
中文关键词: | |
外文关键词: | sentence pattern evaluation ; Chinese ability ; evaluation tools |
中文摘要: |
句子是人们用来进行交际的基本单位。在语言学习过程中,句子是由字词向篇章过渡的重要组成成分,是提高阅读理解能力和写作能力的基础。句式一般认为是句子的格式,句子无限而句式有限。为了获得学生的句式掌握情况,当前教学中大多采用修改病句、造句等题目的形式进行,这类题目没有考虑学生在读写过程中对句式的运用和掌握情况,脱离实际运用情境的测试形式不能改变学生在写作中不愿用、不会用相关句式的情况。因此,本研究希望通过对学生在线读写活动数据的分析,得出其句式掌握水平并予以一定的反馈。三余阅读APP是一款支持学生自主阅读、课堂互动阅读等各类阅读活动的移动软件,它能够支持对学生过程性读写活动数据的收集,本研究基于该产品完成句式自动测评模块的设计与实现。
﹀
本研究首先梳理了小学语文教材中出现的句式,建立句式语料库,明确各年级所需掌握的句式及计算机识别的关键关系词。同时设计基于规则的方法,对学生阅读和写作的过程性数据中出现的句式进行自动识别。之后选取用户在三余阅读APP中的读写活动数据,对其进行分析与计算得出用户的句式掌握水平,并基于以上的功能对句式自动测评模块的界面原型进行设计。在接下来的模块评估阶段,对句式识别算法的正确率进行了检验,通过对用户数据的分析得出该算法的正确率达到88%,具有较高的准确度。最后,在可用性测试中,用户对于该模块的认知有用性和认知易用性评分较高。本研究设计的句式自动测评模块具有较高的有效性、效率和满意度。 |
外文摘要: |
Sentences are the basic units that people use to communicate. In the process of language learning, sentences are an important part of the transition from words to texts, and are the basis for improving reading comprehension and writing ability. Sentence pattern is generally considered to be the format of a sentence, which is finite. In order to obtain students' mastery of sentence patterns, most of the teaching adopts the form of modifying sick sentences, making sentences and other topics, but these kind of test does not consider the students' application and mastery of sentence patterns in the process of reading and writing, and the test divorced from the actual application situation cannot change the students' unwillingness to use or inability to use relevant sentence patterns in writing. Therefore, this study hopes to obtain students' mastery level of sentence patterns and give some feedback by analyzing the data of their online reading and writing activities. SanYu Reading APP is a mobile software that supports students' independent reading, interactive reading in class and other reading activities, and also supports the collection of data of students' online reading and writing activities. This study is based on this product to complete the design and implementation of the sentence pattern automatic evaluation module.
﹀
This study first sorts out the sentence patterns in Chinese teaching materials in the primary school, establishes a corpus of sentence patterns, and clarifies the sentence patterns and key relationship words for each grade. At the same time, a rule-based method is designed to automatically identify the sentence patterns in students' reading and writing process data. Then this study selects the reading and writing activity data of the users in SanYu Reading APP to analyze and calculate the user's mastery of sentence patterns, and design the interface prototype of this module based on the above functions. In the next module evaluation stage, the correctness of the sentence pattern recognition algorithm is tested, and it is concluded that the accuracy of the algorithm reaches 88% through the analysis of user data, which has a high accuracy. Finally, in the usability test, users scored higher on the cognitive usefulness and cognitive ease of use of the module. The sentence pattern automatic evaluation module designed in this study has high effectiveness, efficiency and satisfaction. |
参考文献总数: | 28 |
馆藏号: | 本040104/20005 |
开放日期: | 2021-06-10 |