本論文利用分析電影字幕的對話內容，擷取能具有其代表性的特徵字，並經由相似度的計算將影片分群，進而將具有相對關聯性的影片推薦給使用者。透過系統所推薦的特徵字，使用者可以在影片播放前先進行生字的預習(Preview)；而分群的結果，可以藉由使用者正在觀看的影片推測其他可能有興趣的影集系列，並強化學習相關影集內具有關聯性的字彙。
研究目的主要在營造一個自然的非刻意學習環境，並透過觀賞電影的方式來設計一個非刻意電影英語學習系統，目的希望利用生字預習與同類型影片推薦的方式，來提升學習英語學習的成效。

The purpose of this proposal is to design a learning environment based on movies, so that students will be able to learn how English is used in day-to-day, realistic moments. In addition, the movie subtitles extracted from movies help EFL (English as a Foreign Language) students learn from vocabulary words while watching the movie. By doing so, incidental language learning is achieved. The system can focus on the relative keyword lists provided with the movies subtitles. It also has a preview feature that lets the student review the vocabulary words before watching the movie. This way when the student watches the movie, he will be able to understand the content better. This proposal hopes that by constructing such a system, incidental language learning can be achieved.

目錄
第1章	 緒論	1
1.1	研究動機	2
1.2	研究目的	3
1.3	研究內容	5
1.4	論文內容與大綱	7
第2章	 背景知識與相關研究	8
2.1	影片與語言學習	8
2.1.1	影片在語言學習上的好處	9
2.1.2	影片在教學上使用的缺點	11
2.2	非刻意學習(INCIDENTAL LEARNING)	12
2.3	預習(PREVIEW)	13
第3章 系統架構	15
3.1	字幕來源(OPENSUBTITLES DOWNLOADER)	19
3.1.1	字幕內容前處理	22
3.1.2	正規表示法過濾	23
3.1.3	數字、標點符號及停用字移除	25
3.1.4	關鍵字	28
3.2	相對機率(RELATIVE PROBABILITY)	29
3.2.1	Add-1 平滑化(Add-1 Smoothing)	31
3.3	分群(CLUSTERING)	33
3.3.1	向量空間模式(Vector Space Model)	34
3.4	影片推薦機制	36
第4章	實作與結果	37
4.1	實作系統環境	37
4.2	實作介面	38
4.3	實驗結果與討論	40
第5章	 結論與未來研究方向	41
5.1	結論	41
5.2	未來研究方向	42
參考文獻	43
附錄	46
 
圖目錄
圖3-1	系統流程圖	15
圖3-2 系統處理架構	18
圖3.1-1 SRT字幕檔內對話格式	19
圖3.1-2 OpenSubtitles網站頁面	20
圖3.1-3 SubDownloader下載介面	21
圖3.1.1-1	關鍵字擷取流程圖	22
圖3.1.2-1 對話內容格式分析	23
圖3.1.2-2 字幕檔分析後取出格式內容	24
圖3.1.2-3 對話內容單字擷取	24
圖3.1.3-1 stopword list部分內容	26
圖3.1.3-2 字典內容	27
圖3.1.4-1	初步關鍵字擷取	28
圖3.1.2-2 Add-1 Smoothing後結果	32
圖3.3.1-1 餘弦定理	35
圖3.3.1-2 取得cos角度的向量示意圖	35
圖4.2-1 系統介面	38
圖4.2-2 系統執行畫面	39

表目錄
表3.2-1 字彙出現所在的系列影集範例	30
表4.3-1 由電影中所取出的代表性特徵字與推薦影片	40

[1]Huang, J.” Voices from Chinese student:Professors' use of English affects academic listening”. College Student Journal, 212-224,2004.
[2]Blum, S., & Levenston, E. ”Lexical simplification in second language acquisition”. Studies in Second Language Acquisition, 2, 85-94,1979.
[3]Brown, C. ”Factors affecting the acquisition of vocabulary: Frequency andsaliency of words”. In T. Huckin, M. Haynes & J. Coady (Eds.), Second Languagereading and vocabulary learning (pp. 263-286). Norwood, NJ: Ablex,1990.
[4]Coady, J., Magoto, J., Hubbard, P., Graney, J., & Mokhtari, K. ”High frequency vocabulary and reading proficiency in ESL readers”. In T. Huckin, M. Haynes & J.Coady (Eds.), Second language reading and vocabulary learning (pp. 217-228).Norwood, NJ: Ablex,1993.
[5]Hung Tsung-Fu, Chiou Yan-Shiang, Kuo Chin-Hwa, Tsao Nai-Lung,“A Personalized Movies System for English Learning”, International Computer Symposiums ICS-2008, Taiwan, Nov 13-15, 2008.
[6]De Bot, K., Paribakht, T. S., & Wesche, M. ”Toward a lexical processing model for the study of second language vocabulary acquisition”. Studies in Second Language Acquisition, 19, 309-329,1997.
[7]Jane King. “Using DVD feature films in project-based learning“.CALL Review. International Association of Teaching Englishas a Foreign Language (IATEFL), UK. P.45-49, Sep. 2003.
[8]Erwin Tschirner “Breadth of Vocabulary and Advanced English Study: AnEmpirical Investigation”. Electronic Journal of Foreign Language Teaching, Vol. 1, No.1, 27-39,2004.
[9]Hazenberg, S., & Hulstijn, J.H. ”Defining a minimal receptive second-language vocabulary for non-native university students: An empirical investigation”. Applied Linguistics, 17, 145-163,1996.
[10]Huckin, T., & Coady, J. ”Incidental vocabulary acquisition in a second language: A review”. Studies in Second Language Acquisition, 21, 181–193,1999.
[11]OpenSubtitles  Http://www.opensubtitles.org
[12]Hulstijn, J. H.”Retention of given and inferred word meaning: Experiments in incidental vocabulary learning”. In P. J. L. Arnud & H. Bejoint (Eds.), Vocabulary and applied linguistics (pp. 113-125). London: Macmillan,1992.
[13]Joe, A. ”Text-based tasks and incidental vocabulary learning”. Second Language Research, 11, 149-158,1995.
[14]Marsick, V. J., & Watkins, K.”Informal and incidental learning in the workplace”. London: Routledge,1990.
[15]Paribakht, T., & Wesche, M.”Reading and incidental L2 vocabulary acquisition: An introspective study of lexical inferencing”. Studies in Second Language Acquisition, 21, 195-224,1999.
[16]Pulido, D. ” The relationship between text comprehension and second language incidental vocabulary acquisition: A matter of topic familiarity”. Language Learning,54, 469-523,2004.
[17]Rott, S.”The effect of exposure frequency on intermediate language learners’ incidental vocabulary acquisition through reading”. Studies in Second language Acquisition 21, 589-619,1999.
[18]Shu, H., Anderson, R. C., & Zhang, H.”Incidental learning of word meanings while reading: A Chinese and American cross-cultural study”. Reading Research Quarterly, 30, 76-95,1995.
[19]Swanborn, M. S. L., & de Glopper, K. ”Impact of reading purpose on incidental word learning from context”. Language Learning, 52, 95–117,2002.
[20]Hung Tsung-Fu, Chen Ruey-Jinng, Kuo Chin-Hwa, Tsao Nai-Lung,“Improving the Syntax-based Retrieval System Using Collocation Indexing”, International Computer Symposiums ICS-2008, Taiwan, Nov 13-15, 2008.