簡易檢索 / 詳目顯示

回結果列表
研究生： 陳致丞
Chen, Zhi-Cheng
論文名稱： 探討 AI 圖像生成對應英語詞彙與介面可用性評估
Discussing the assessment of AI image generation corresponding English vocabulary and interface usability
指導教授： 劉說芳
Liu, Shuo-Fang
學位類別： 碩士
Master
系所名稱： 規劃與設計學院 - 工業設計學系
Department of Industrial Design
論文出版年： 2025
畢業學年度： 113
語文別： 英文
論文頁數： 264
中文關鍵詞： 人工智能 、介面可用性評估 、文生圖
外文關鍵詞： Artificial Intelligence, Interface Usability Evaluation, Text-to-Image
相關次數： 點閱：62  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 隨著科技的不斷進步，英文學習方式與工具也在不斷演變。其中，圖像學習法作為一種透過圖像提升詞彙記憶的方法備受關注。然而，不論是具體或抽象詞彙，圖像表達詞彙語意持續被挑戰。在人工智慧(Artificial Intelligence，AI)技術的發展，尤其是 AI 圖像生成工具的快速發展，為圖像的產生與應用提供截然不同的影響。另一方面，“牛津圖片詞典|視覺英語”一款Google擴充功能，利用圖像學習法概念幫助圖像與詞彙建立連結，輔助學習者學習英文詞彙，但在介面呈現上影響詞彙學習。本研究旨在探討AI圖像生成技術對英文詞彙學習的潛在影響及應用，並評估其相較於現有圖像學習工具的優勢與不足。研究採用介面可用性評估，以成對樣本t檢定比較重新設計的介面與現有圖像的介面差異。研究結果顯示，“牛津詞典＋AI生成圖像”介面在介面設計、功能操作、學習動機與未來使用意願等方面均表現優異，證實AI圖像生成技術有助提升英文詞彙學習效率。另外透過實驗收集圖像評級的數據，包括圖像一致性評級、視覺複雜性評級、圖像排序評級，探討現有圖像與AI生成圖像在表現上是否存在顯著差異，分析出具體詞彙與抽象詞彙對心像建立、圖像視覺複雜程度以及圖像對於詞彙代表性的排序認知，討論彼此間的關聯性與表現。結果發現AI生成圖像在低具體性詞彙中展現較佳表現，能創造性地表達抽象語義，貼合學習者心理預期。而現有圖像則在高具體性詞彙的學習上具優勢，能提供更精準的語義對應。儘管如此，AI技術在部分情境下仍面臨挑戰，例如人物或物件細節不自然，以及專有名詞和特定詞彙表現力不足。最後，本研究的實驗限制包括詞彙分類方法僅以低具體性與高成像性等四個象限為依據，未全面涵蓋詞彙特性，在僅選取28個詞彙進行測試下，可能限制結果的廣泛適用性。

    The rapid advancement of technology has significantly transformed English learning methods and tools, with image-based learning gaining attention as a technique that enhances vocabulary retention through visual aids. However, the representation of vocabulary semantics via images, whether for concrete or abstract terms—remains challenging. The development of Artificial Intelligence (AI), particularly in AI-powered image generation tools, introduces new dimensions to the creation and application of visual aids. One notable tool, Oxford Picture Dictionary | Visual English, a Google extension, employs image-based learning to link visuals with vocabulary, aiding learners in their English studies. However, its interface design may impact vocabulary acquisition. This study investigates the potential influence and applications of AI-generated imagery on English vocabulary learning, evaluating its advantages and shortcomings compared to existing image-based tools. Using interface usability assessments, the study applied paired-sample t-tests to compare a redesigned interface incorporating AI-generated images against the existing visual interface. The results reveal that Oxford Dictionary + AI-generated Images interface excels in design, functionality, user motivation, and future usage intent, demonstrating that AI-generated imagery can enhance vocabulary learning efficiency. Furthermore, experimental data were collected on image evaluations, including image agreement, visual complexity, and image ranking, to explore performance differences between existing visuals and AI-generated images. The study also analyzed the correlation between imagery and vocabulary representation, focusing on concrete and abstract terms. Findings indicate that AI-generated images perform better for low-concreteness vocabulary, creatively expressing abstract semantics and aligning with learners' psychological expectations. Conversely, existing visuals are more effective for high-concreteness vocabulary, offering precise semantic correspondence. Despite these advantages, AI-generated images face challenges in certain contexts, such as unnatural details in people or objects and insufficient representation of proper nouns or specific terms.

    摘要 ii SUMMARY iii ACKNOWLEDGEMENTS iv TABLE OF CONTENTS v LIST OF TABLES viii LIST OF FIGURES xiii LIST OF SYMBOLS AND ABBREVIATIONS xv CHAPTER 1 INTRODUCTION 16 1.1 Research Background 16 1.2 Research Motivation 17 1.3 Research Purpose 19 1.4 Research Scope and Limitation 19 1.5 Research Structure 21 CHAPTER 2 LITERATURE REVIEW 22 2.1 English Learning Strategies 22 2.1.1 Introduction to English Vocabulary 22 2.1.2 Vocabulary Learning Strategies 22 2.1.3 Oxford Picture Dictionary 24 2.2 Interface Layout Design 27 2.2.1 Comparison of Dictionary Layout 28 2.3 Concreteness and Abstraction 30 2.3.1 Dual-Coding Theory 31 2.3.2 Mental Imagery32 2.3.3 Presentation of Abstract Concepts 33 2.3.4 Imageability 34 2.4 AI Image Generation 35 2.4.1 Introduction to AI Image Generation 35 2.4.2 Leonardo.Ai 37 2.5 Summery 40 CHAPTER 3 Research Method and Design 42 3.1 Experimental Procedure 42 3.2 Research Methods and Tools 44 3.2.1 Equipment 44 3.2.2 Interview Methodology 44 3.2.3 MRC Psycholinguistic Database 45 3.2.4 System Usability Scale Evaluation 45 3.2.5 Paired Sample T Test 48 3.2.6 Correlation Analysis 50 3.2.7 Friedman and Wilcoxon Signed-Rank Tests 51 3.3 Vocabulary Selection 53 3.3.1 Selection Method 53 3.3.2 Final Experimental Vocabulary 55 3.4 Interface Design 56 3.4.1 Interface Prototype Development 56 3.4.2 Interface Design Analysis 59 3.4.3 Interface Prototype Development 60 3.4.4 Experimental Interface Selection 62 3.5 Image Preparation 65 3.5.1 Prerequisites 65 3.5.2 Prompt Extraction Logic 67 3.5.3 Final Experimental Image 70 3.6 Experiment and Statistical Analysis 72 3.6.1 Participant 72 3.6.2 Experiment (Figure 3.8) 73 3.6.3 Statistical Analysis 77 CHAPTER 4 Research Method and Design 80 4.1 Dictionary Interface Analysis 80 4.1.1 Reliability Analysis 80 4.1.2 Paired Samples T-Test 81 4.2 Image rating analysis 86 4.2.1 Correlation Analysis 87 4.2.2 Differences in Image Agreement 96 4.2.3 Image Ranking Evaluation 107 4.3 Summary of Results121 CHAPTER 5 DISCUSSION 124 5.1 Interface Discussion 124 5.1.1 Perceptions and Experiences of Interface 124 5.1.2 Challenges in Comparing Interfaces 125 5.1.3 Perspectives on Interface Comparison 125 5.2 Image Rating Discussion 126 5.2.1 Image Rating Observation 126 5.2.2 Experiences and Impressions of Image Rating 127 5.2.3 Challenges in Image Rating 127 5.2.4 Experiences and Impressions of Image Rating 128 5.3 Discussion Summary 129 5.4 Suggestions and Ideas 131 CHAPTER 6 CONCLUSION 132 REFERENCES 134 Appendix A Preparing Images for Experiments 142 Appendix B Rating Description 171 Appendix C Image Ranking Rating Description 195

    Chinese References
    史天元, & 黃中偉. （2000）. 排序評分法篩選標準探討。地籍測量: 中華民國地籍測量學會會刊，19(4)，1-15。[Shih, T. Y., & Ｈuang, Z. W. (2000). The Discussion on Selection Criteria of Ranking Scoring Method. Journal of Cadastral Survey, 19(4), 1-15.]
    蘇安愉. （2022）. 結合智慧技術並應用概念構圖法於移動英語詞彙學習 APP 設計. 台南市：國立成功大學工業設計研究所。[Su, A. Y. (2022). Combining Smart Technology and Concept Mapping Method to design a mobile English vocabulary learning APP. National Cheng Kung University, Tainan City, Taiwan, ROC.]
     
    English References
    Alemi, M., Sarab, M. R. A., & Lari, Z. (2012). Successful learning of academic word list via MALL: Mobile Assisted Language Learning. International Education Studies, 5(6), 99-109
    Algozzine, B., & Douville, P. (2004). Use mental imagery across the curriculum. Preventing School Failure: Alternative Education for Children and Youth, 49(1), 36-39.
    Alhamami, M. (2016). Vocabulary learning through audios, images, and videos: Linking technologies with memory. Call-Ej, 17(2), 87-112.
    Atkinson, R. C., & Shiffrin, R. M. (1968). Human memory: A proposed system and its control processes. In Psychology of learning and motivation (Vol. 2, pp. 89-195): Elsevier.
    Bai, Z. (2018). An analysis of English vocabulary learning strategies. Journal of language Teaching and Research, 9(4), 849-855.
    Balota, D. A., Cortese, M. J., Sergent-Marshall, S. D., Spieler, D. H., & Yap, M. J. (2004). Visual word recognition of single-syllable words. Journal of experimental psychology: General, 133(2), 283.
    Barcroft, J. (2009). Strategies and performance in intentional L2 vocabulary learning. Language awareness, 18(1), 74-89.
    Binder, J. R., & Desai, R. H. (2011). The neurobiology of semantic memory. Trends in cognitive sciences, 15(11), 527-536.
    Bird, H., Franklin, S., & Howard, D. (2001). Age of acquisition and imageability ratings for a large set of words, including verbs and function words. Behavior Research Methods, Instruments, & Computers, 33(1), 73-79.
    Brynjolfsson, E., & Mcafee, A. (2017). Artificial intelligence, for real. Harvard business review, 1, 1-31.
    Brysbaert, M., Mandera, P., McCormick, S. F., & Keuleers, E. (2019). Word prevalence norms for 62,000 English lemmas. Behavior research methods, 51, 467-479.
    Chen, A.-h. (2013). Parents' perspectives on the effects of the primary EFL education policy in Taiwan. In Language planning in primary schools in Asia (pp. 101-120): Routledge.
    Chen, C.-M., Chen, L.-C., & Yang, S.-M. (2019). An English vocabulary learning app with self-regulated learning mechanism to improve learning performance and motivation. Computer Assisted Language Learning, 32(3), 237-260.
    Chen, C.-M., & Chung, C.-J. (2008). Personalized mobile English vocabulary learning system based on item response theory and learning memory cycle. Computers & Education, 51(2), 624-645.
    Cheung Matthew Sung, C. (2013). Learning English as an L2 in the global context: Changing English, changing motivation. Changing English, 20(4), 377-387.
    Cho, V., Cheng, T. E., & Lai, W. J. (2009). The role of perceived user-interface design in continued usage intention of self-paced e-learning tools. Computers & Education, 53(2), 216-227.
    Chong, M. J., & Forsyth, D. (2020). Effectively unbiased fid and inception score and where to find them. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
    Chun, D. M., & Plass, J. L. (1996). Effects of multimedia annotations on vocabulary acquisition. The modern language journal, 80(2), 183-198.
    Clark, J. M., & Paivio, A. (1991). Dual coding theory and education. Educational psychology review, 3, 149-210.
    Coltheart, M. (1981). The MRC psycholinguistic database. The Quarterly Journal of Experimental Psychology Section A, 33(4), 497-505.
    Dimitropoulou, M., Duñabeitia, J. A., Blitsas, P., & Carreiras, M. (2009). A standardized set of 260 pictures for Modern Greek: Norms for name agreement, age of acquisition, and visual complexity. Behavior research methods, 41(2), 584-589.
    Dörnyei, Z., & Csizér, K. (2002). Some dynamics of language attitudes and motivation: Results of a longitudinal nationwide survey. Applied linguistics, 23(4), 421-462.
    Farley, A. P., Ramonda, K., & Liu, X. (2012). The concreteness effect and the bilingual lexicon: The impact of visual stimuli attachment on meaning recall of abstract L2 words. Language teaching research, 16(4), 449-466.
    Ganis, G., & Schendan, H. E. (2011). Visual imagery. Wiley Interdisciplinary Reviews: Cognitive Science, 2(3), 239-252.
    Ghasisin, L., Yadegari, F., Rahgozar, M., Nazari, A., & Rastegarianzade, N. (2015). A new set of 272 pictures for psycholinguistic studies: Persian norms for name agreement, image agreement, conceptual familiarity, visual complexity, and age of acquisition. Behavior research methods, 47, 1148-1158.
    Gilhooly, K. J., & Logie, R. H. (1980). Age-of-acquisition, imagery, concreteness, familiarity, and ambiguity measures for 1,944 words. Behavior research methods & instrumentation, 12(4), 395-427.
    Hu, G., & McKay, S. L. (2012). English language education in East Asia: Some recent developments. Journal of Multilingual and Multicultural Development, 33(4), 345-362.
    Ilyosovna, N. A. (2020). The importance of English language. International Journal on Orange Technologies, 2(1), 22-24.
    Jing, Y., Yang, Y., Feng, Z., Ye, J., Yu, Y., & Song, M. (2019). Neural style transfer: A review. IEEE transactions on visualization and computer graphics, 26(11), 3365-3385.
    Komachali, M. E., & Khodareza, M. (2012). The Effect of Using Vocabulary Flash Card on Iranian Pre-University Students' Vocabulary Knowledge. International Education Studies, 5(3), 134-147.
    Kvale, S., & Brinkmann, S. (2009). Interviews: Learning the craft of qualitative research interviewing: sage.
    Leavitt, M. O., & Shneiderman, B. (2006). Based web design & usability guidelines. Background and Methodology.
    Lin, C.-C., & Yu, Y.-C. (2017). Effects of presentation modes on mobile-assisted vocabulary learning and cognitive load. Interactive Learning Environments, 25(4), 528-542.
    Liu, X. (2020). Artistic reflection on artificial intelligence digital painting. Paper presented at the Journal of Physics: Conference Series.
    Luckner, J. L., & Cooke, C. (2010). A summary of the vocabulary research with students who are deaf or hard of hearing. American annals of the deaf, 155(1), 38-67.
    Lyu, Y., Wang, X., Lin, R., & Wu, J. (2022). Communication in human–AI co-creation: Perceptual analysis of paintings generated by text-to-image system. Applied Sciences, 12(22), 11312.
    Mayer, R. E. (1999). Multimedia aids to problem-solving transfer. International Journal of Educational Research, 31(7), 611-623.
    Novak, J. D. (2004). Concept maps and how to use them. Insight, 6(2), 15-16.
    Oxford, R., & Crookall, D. (1990). Vocabulary learning: A critical analysis of techniques. TESL Canada journal, 09-30.
    Paivio, A. (1969). Mental imagery in associative learning and memory. Psychological review, 76(3), 241.
    Paivio, A. (1990). Mental representations: A dual coding approach: Oxford university press.
    Paivio, A. (2014a). Bilingual dual coding theory and memory. Foundations of bilingual memory, 41-62.
    Paivio, A. (2014b). Intelligence, dual coding theory, and the brain. Intelligence, 47, 141-158.
    Paivio, A., Yuille, J. C., & Madigan, S. A. (1968). Concreteness, imagery, and meaningfulness values for 925 nouns. Journal of experimental psychology, 76(1p2), 1.
    Pan, W. F. (2017). The Effects of using the Kinect motion-sensing interactive system to enhance English learning for elementary students. Journal of Educational Technology & Society, 20(2), 188-200.
    Petilli, M. A., Günther, F., & Marelli, M. (2024). The Flickr frequency norms: what 17 years of images tagged online tell us about lexical processing. Behavior research methods, 56(1), 126-147.
    Petilli, M. A., & Marelli, M. (2024). Visual intuitions in the absence of visual experience: the role of direct experience in concreteness and imageability judgements. Journal of Cognition, 7(1).
    Pezzulo, G., Parr, T., Cisek, P., Clark, A., & Friston, K. (2024). Generating meaning: active inference and the scope and limits of passive AI. Trends in cognitive sciences, 28(2), 97-112.
    Ponari, M., Norbury, C. F., Rotaru, A., Lenci, A., & Vigliocco, G. (2018). Learning abstract words and concepts: insights from developmental language disorder. Philosophical Transactions of the Royal Society B: Biological Sciences, 373(1752), 20170140.
    Qiao, H., Liu, V., & Chilton, L. (2022). Initial images: using image prompts to improve subject representation in multimodal ai generated art. Paper presented at the Proceedings of the 14th Conference on Creativity and Cognition.
    Richardson, J. T. (1998). The availability and effectiveness of reported mediators in associative learning: A historical review and an experimental investigation. Psychonomic Bulletin & Review, 5, 597-614.
    Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
    Roose, K. (2022). An AI-generated picture won an art prize. Artists aren’t happy. The New York Times, 2(September).
    Schmitt, N. (2008). Instructed second language vocabulary learning. Language teaching research, 12(3), 329-363.
    Schwanenflugel, P. J., Harnishfeger, K. K., & Stowe, R. W. (1988). Context availability and lexical decisions for abstract and concrete words. Journal of memory and language, 27(5), 499-520.
    Shadiev, R., Wu, T.-T., & Huang, Y.-M. (2020). Using image-to-text recognition technology to facilitate vocabulary acquisition in authentic contexts. ReCALL, 32(2), 195-212.
    Shaikh, S., Yayilgan, S. Y., Klimova, B., & Pikhart, M. (2023). Assessing the usability of ChatGPT for formal english language learning. European Journal of Investigation in Health, Psychology and Education, 13(9), 1937-1960.
    Shen, H. H. (2010). Imagery and verbal coding approaches in Chinese vocabulary instruction. Language teaching research, 14(4), 485-499.
    Smith, G. G., Li, M., Drobisz, J., Park, H.-R., Kim, D., & Smith, S. D. (2013). Play games or study? Computer games in eBooks to learn English vocabulary. Computers & Education, 69, 274-286.
    Snodgrass, J. G., & Vanderwart, M. (1980). A standardized set of 260 pictures: norms for name agreement, image agreement, familiarity, and visual complexity. Journal of experimental psychology: Human learning and memory, 6(2), 174.
    Stadthagen-Gonzalez, H., & Davis, C. J. (2006). The Bristol norms for age of acquisition, imageability, and familiarity. Behavior research methods, 38(4), 598-605.
    Stoller, F. (2002). Project work: A means to promote language and content. Methodology in language teaching: An anthology of current practice, 10, 107-119.
    Tankersley, K. (2003). The THREADS OF READING STRATEGS FOR LITERACY DEVELOPMENT. In: USA.
    Vellutino, F. R., & Scanlon, D. M. (1985). Free recall of concrete and abstract words in poor and normal readers. Journal of experimental Child psychology, 39(2), 363-380.
    Vignali, L., Xu, Y., Turini, J., Collignon, O., Crepaldi, D., & Bottini, R. (2023). Spatiotemporal dynamics of abstract and concrete semantic representations. Brain and language, 243, 105298.
    Wang, H. Y., & Utama, S. (2023). Investigating the generative-ai evaluation methods and correlation with fashion designers. Paper presented at the 2023 7th International Conference on Information Technology (InCIT).
    West, C. K., Farmer, J. A., & Wolff, P. M. (1991). Instructional design: Implications from cognitive science. (No Title).
    Wu, T. T. (2018). Improving the effectiveness of English vocabulary review by integrating ARCS with mobile game‐based learning. Journal of Computer Assisted Learning, 34(3), 315-323.
    Xu, J., Zhang, X., Li, H., Yoo, C., & Pan, Y. (2023). Is Everyone an Artist? A Study on User Experience of AI-Based Painting System. Applied Sciences, 13(11), 6496.
    Zhang, C., Wang, W., Pangaro, P., Martelaro, N., & Byrne, D. (2023). Generative Image AI Using Design Sketches as input: Opportunities and Challenges. Paper presented at the Proceedings of the 15th Conference on Creativity and Cognition.

    Internet Data
    ThePictureDictionary (2020). 牛津圖片詞典| 視覺英語. 取自 https://chromewebstore.google.com/detail/ekffngdiljhjmmmfcajfmpheedkonklc
    [ThePictureDictionary, (2020) Oxford Picture Dictionary | Visual English Retrieved from https://chromewebstore.google.com/detail/ekffngdiljhjmmmfcajfmpheedkonklc]
    AUTOMATIC1111(2022). Stable Diffusion webui. Retrieved from https://github.com/AUTOMATIC1111/stable-diffusion-webui
    Duolingo (2024) Duolingo - The world's best way to learn a language Retrieved from https://en.duolingo.com/
    IBM (2021) Correlations: Statistics Retrieved from https://www.ibm.com/docs/en/spss-statistics/beta?topic=correlations-statistics
    IBM (2021b) One-way ANOVA: Post hoc tests Retrieved from https://www.ibm.com/docs/hu/spss-statistics/beta?topic=anova-one-way-post-hoc-tests
    IBM(2021c) Friedman test Retrieved from https://www.ibm.com/docs/hu/spss-statistics/beta?topic=tests-friedman-test
    IBM (2023) factor analysis Retrieved from https://www.ibm.com/docs/zh-tw/spss-statistics/saas?topic=features-factor-analysis#idh_fact
    JMP User Community (2024) t test Retrieved fromhttps://www.jmp.com/zh_tw/statistics-knowledge-portal/t-test.html
    Leonardo. Ai (2024) Leonardo AI: AI Art Generator - Create Art, Images & More Retrieved from https://leonardo.ai/
    Midjourney (2022) Midjourney Retrieved from https://www.midjourney.com
    Nielsen, J. (2006) F-Shaped Pattern For Reading Web Content (original study) Retrieved from https://www.nngroup.com/articles/f-shaped-pattern-reading-web-content-discovered/
    Nielsen, J. (2024) 10 Usability Heuristics for User Interface Design Retrieved from https://www.nngroup.com/articles/ten-usability-heuristics/
    OpenAI (2022) ChatGPT Retrieved from https://openai.com/chatgpt
    OpenAI (2024) DALL·E 3 Retrieved from https://openai.com/dall-e-3
    Oxford University (2024) Oxford Learner's Dictionaries | Find definitions, translations ... Retrieved from https://www.oxfordlearnersdictionaries.com/
    Princeton University (2010) WordNet Retrieved from https://wordnet.princeton.edu/
    Quizlet (2024) Quizlet: Flashcards, learning tools and textbook solutions Retrieved from https://quizlet.com/tw
    Stability. Ai (2024) Stability AI Retrieved from https://stability.ai/
    VoiceTube (2024) VoiceTube | Learning English Online through Videos Retrieved from https://www.voicetube.com/
    Wikipedia (2023) Descriptive statistics Retrieved from https://en.wikipedia.org/wiki/Descriptive_statistics
    Wikipedia (2024a) Correlation Retrieved from https://en.wikipedia.org/wiki/Correlation
    Wikipedia (2024b) Cronbach's alpha Retrieved from https://en.wikipedia.org/wiki/Cronbach%27s_alpha
    Wikipedia (2024c) Friedman test Retrieved from https://en.wikipedia.org/wiki/Friedman_test
    Wikipedia (2024d) Wilcoxon signed-rank test Retrieved from https://en.wikipedia.org/wiki/Wilcoxon_signed-rank_test
    WordMapDictionary (2021) WordMapDictionary Retrieved from https://wordmapdictionary.com/

    無法下載圖示 校內：2030-01-31公開
    校外：2030-01-31公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE