學術產出-Theses
Article View/Open
Publication Export
-
題名 透過圖片標籤觀察情緒字詞與事物概念之關聯
An analysis on association between emotion words and concept words based on image tags作者 彭聲揚
Peng, Sheng-Yang貢獻者 劉吉軒
Liu, Jyi-Shane
彭聲揚
Peng, Sheng-Yang關鍵詞 情緒分類
情緒檢索
情緒詞
社群網路
字詞共現
關聯 規則
影像與情緒
sentiment classification
sentiment retrieval
sentiment words
word co-occurrence
association rules
image and emotion
social network日期 2010 上傳時間 1-Oct-2013 13:46:41 (UTC+8) 摘要 本研究試圖從心理學出發，探究描述情緒狀態的分類方法為何， 為了進行情緒與語意的連結，我們試圖將影像當作情緒狀態的刺激 來源，針對Flickr網路社群所共建共享的內容進行抽樣與觀察，使 用心理學研究中基礎的情緒字詞與詞性變化，提取12,000張帶有字 詞標籤的照片，進行標籤字詞與情緒分類字詞共現的計算、關聯規則 計算。同時，透過語意差異量表，提出了新的偏向與強度的座標分類 方法。 透過頻率門檻的過濾、詞性加註與詞幹合併字詞的方法，從 65983個不重複的文字標籤中，最後得到272個帶有情緒偏向的事物 概念字詞，以及正負偏向的情緒關聯規則。為了透過影像驗證這些字 詞是否與影像內容帶給人們的情緒狀態有關聯，我們透過三種查詢 管道：Flickr單詞查詢、google image單詞查詢、以及我們透過照片 標籤綜合指標：情緒字詞比例、社群過濾參數來選定最後要比較的 42張照片。透過語意差異量表，測量三組照片在136位使用者的答案 中，是否能吻合先前提出的強度-偏向模型。 實驗結果發現，我們的方法和google image回傳的結果類似， 使用者問卷調查結果支持我們的方法對於正負偏向的判定，且比 google有更佳的強弱分離程度。
This study attempts to proceed from psychology to explore the emotional state of the classification method described why, in order to be emotional and semantic links, images as we try to stimulate the emotional state of the source, the Internet community for sharing Flickr content sampling and observation, using basic psychological research in terms of mood changes with the parts of speech, with word labels extracted 12,000 photos, label and classification of words and word co-occurrence of emotional computing, computing association rules. At the same time, through the semantic differential scale, tend to put forward a new classification of the coordinates and intensity. Through the frequency threshold filter, filling part of speech combined with the terms of the method stems from the 65,983 non-duplicate text labels, the last 272 to get things with the concept of emotional bias term, and positive and negative emotions tend to association rules. In order to verify these words through images is to bring people`s emotional state associated with our pipeline through the three sources: Flickr , google image , and photos through our index labels: the proportion of emotional words, the community filtering parameters to select the final 42 photos to compare. Through the semantic differential scale, measuring three photos in 136 users of answers, whether the agreement made earlier strength - bias model. Experimental results showed that our methods and google image similar to the results returned, the user survey results support our approach to determine the positive and negative bias, and the strength of better than google degree of separation.參考文獻 [1] J. Darley, S. Glucksberg, R. Kinchla ,Psychology , Prentice Hall College Div.5th edition ,1991. [2] E. Fox, Emotion Science： Cognitive and Neuroscientific Approaches to Understanding Human Emotions. Palgrave Macmillan, Sep. 2008. [3] R. W. Picard, E. Vyzas, and J. Healey, "Toward machine emotional intelligence： Analysis of affective physiological state", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1175-1191, Oct. 2001. [4] R. W. Picard, Affective computing. The MIT Press, 1997. [5] P Shaver, J Schwartz, D Kirson, `` Emotion knowledge： Further exploration of a prototype approach``. Journal of Personality and Social Psychology, Vol 52(6), 1061- 1086, 1987. [6] MJ. Power, T. Dalgleish, Cognition and emotion. From order to disorder. Hove, East Sussex, UK： Psychology Press, 1997. [7] C.E. Izard, The Psychology of Emotions, New York, London： Plenum Press, 1991 [8] J.A. Russell, “A circumplex model of affect”. Journal of Personality and Social Psychology, 39(6)：1161-1178, 1980. [9] J. Posner, J. A. Russell, and B. S. Peterson, "The circumplex model of affect： An integrative approach to affective neuroscience, cognitive development, and psychopathology", Development and Psychopathology, vol. 17, no. 03, pp. 715-734, 2005. 86 ‧ 國 立 政 治 大 學 ‧ N a t i on a l Ch e n g c h i U n i v e r s i t y [10] R. Valitutti, "WordNet-affect：an affective extension of WordNet". Proceedings of the 4th International Conference on Language Resources and Evaluation, vol. 2004, pp. 1083-1086, 2004. [11] B. Sigurbjörnsson and R. van Zwol, "Flickr tag recommendation based on collective knowledge". Proceeding of the 17th international conference on World Wide Web, ser. WWW `08. New York, NY, USA： ACM, pp. 327-336, 2008. [12] R. Jonathon Read, “Recognising affect in text using pointwise-mutual information”. master degree thesis ,University of Sussex , 2004. [13] R. Agrawal and R. Srikant, "Fast algorithms for mining association rules". Proc. 20th Int. Conf. Very Large Data Bases, VLDB, pp. 487-499, 1994. [14] M. F. Porter, "An algorithm for suffix stripping". Program, vol. 14, no. 3, pp. 130-137, 1980. [15] D. A. Hull, "Stemming algorithms： A case study for detailed evaluation". Journal of the American Society for Information Science, vol. 47, no. 1, pp. 70-84, Dec. 1998. [16] J. Xu and B. W. Croft, "Corpus-Based stemming using cooccurrence of word variants". ACM Transactions on Information Systems, vol. 16, no. 1, pp. 61-81, 1998. [17] C. E. Osgood, "Semantic differential technique in the comparative study of cultures1," American Anthropologist, vol. 66, no. 3, pp. 171-200, 1964. [18] J. Berger , Ways of Seeing. Penguin ,1972 . [19] S. Schmidt and W. G. Stock, "Collective indexing of emotions in images. a study in emotional information retrieval", Journal of the American Society for Information Science and Technology, vol. 60, no. 5, pp. 863-876, 2009. [20] J. San Pedro and S. Siersdorfer, "Ranking and classifying attractiveness of photos in 87 ‧ 國 立 政 治 大 學 ‧ N a t i on a l Ch e n g c h i U n i v e r s i t y folksonomies”. Proceedings of the 18th international conference on World wide web, ser. WWW `09. New York, NY, USA： ACM, pp. 771-780, 2009. [21] J. Beaudoin, "Folksonomies： Flickr image tagging： Patterns made visible". Bul. Am. Soc. Info. Sci. Tech., vol. 34, no. 1, pp. 26-29, 2007. [22]鄭學侖，「以web2.0民眾分類法建置音樂推薦系統之研究」，國立政治大學資訊 管理研究所碩士論文。 [23] A.J. Gill, D.Gergle, R.M. French, and J.Oberlander, "Emotion rating from short blog texts", Proceeding of the twenty-sixth annual SIGCHI conference on Human factors in computing systems, ser. CHI `08. New York, NY, USA： ACM, pp. 1121-1124, 2008. [24] E. Zheleva, J. Guiver, E. M. Rodrigues, and N. M. Frayling, "Statistical models of music-listening sessions in social media", Proceedings of the 19th international conference on World wide web, ser. WWW `10. New York, NY, USA： ACM, pp. 1019- 1028, 2010. [25] S. Siersdorfer, E. Minack, F. Deng, and J. Hare, "Analyzing and predicting sentiment of images on the social web". Proceedings of the international conference on Multimedia, ser. MM `10. New York, NY, USA： ACM, pp. 715-718, 2010. [26] G.Grefenstette , “Comparing the Language Used in Flickr, General Web Pages, Yahoo Images and Wikipedia”. LREC08 proceedings, 6-11, 2008. [27] L. Kennedy, M. Naaman, S. Ahern, R. Nair, and T. Rattenbury, "How Flickr helps us make sense of the world： context and content in community-contributed media collections". Proceedings of the 15th international conference on Multimedia, ser. MULTIMEDIA `07. New York, NY, USA： ACM, pp. 631-640, 2007. [28] C. Marlow, M. Naaman, D. Boyd, and M. Davis, "HT06, tagging paper, taxonomy, 88 ‧ 國 立 政 治 大 學 ‧ N a t i on a l Ch e n g c h i U n i v e r s i t y Flickr, academic article, to read". Proceedings of the seventeenth conference on Hypertext and hypermedia, ser. HYPERTEXT `06. New York, NY, USA： ACM, pp. 31- 40, 2006. [29] G. Begelman, "Automated tag clustering： Improving search and exploration in the tag space". Proceeding of the Collaborative Web Tagging Workshop at WWW`06, 2006. [30] 吳筱玫、周芷伊，「Tagging的分類與知識意涵：以Flickr首頁圖片為例」，新聞學 研究，台北，2009年4月，頁265-305 [31] Mikels, J. A., Fredrickson, B. L., Larkin, G. R., Lindberg, C. M., Maglio, S. J., and Reuter-Lorenz, P. A. (2005). Emotional category data on images from the international affective picture system. Behavior Research Methods, 37(4):626-630. [32] Lang, P. J. (1995). The emotion probe. studies of motivation and attention. The American psychologist, 50(5):372-385. [33] Peter Mika. (2007). “Ontologies are us: emergent semantics in folksonomy systems In Social Networks and the Semantic Web”. International Semantic Web Conference, International Semantic Web Conference (ISWC2005), Vol. 5, No. 1. (March 2007), pp. 5-15 描述 碩士
國立政治大學
資訊科學學系
95753015
99資料來源 http://thesis.lib.nccu.edu.tw/record/#G0095753015 資料類型 thesis dc.contributor.advisor 劉吉軒 zh_TW dc.contributor.advisor Liu, Jyi-Shane en_US dc.contributor.author (Authors) 彭聲揚 zh_TW dc.contributor.author (Authors) Peng, Sheng-Yang en_US dc.creator (作者) 彭聲揚 zh_TW dc.creator (作者) Peng, Sheng-Yang en_US dc.date (日期) 2010 en_US dc.date.accessioned 1-Oct-2013 13:46:41 (UTC+8) - dc.date.available 1-Oct-2013 13:46:41 (UTC+8) - dc.date.issued (上傳時間) 1-Oct-2013 13:46:41 (UTC+8) - dc.identifier (Other Identifiers) G0095753015 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/61196 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學學系 zh_TW dc.description (描述) 95753015 zh_TW dc.description (描述) 99 zh_TW dc.description.abstract (摘要) 本研究試圖從心理學出發，探究描述情緒狀態的分類方法為何， 為了進行情緒與語意的連結，我們試圖將影像當作情緒狀態的刺激 來源，針對Flickr網路社群所共建共享的內容進行抽樣與觀察，使 用心理學研究中基礎的情緒字詞與詞性變化，提取12,000張帶有字 詞標籤的照片，進行標籤字詞與情緒分類字詞共現的計算、關聯規則 計算。同時，透過語意差異量表，提出了新的偏向與強度的座標分類 方法。 透過頻率門檻的過濾、詞性加註與詞幹合併字詞的方法，從 65983個不重複的文字標籤中，最後得到272個帶有情緒偏向的事物 概念字詞，以及正負偏向的情緒關聯規則。為了透過影像驗證這些字 詞是否與影像內容帶給人們的情緒狀態有關聯，我們透過三種查詢 管道：Flickr單詞查詢、google image單詞查詢、以及我們透過照片 標籤綜合指標：情緒字詞比例、社群過濾參數來選定最後要比較的 42張照片。透過語意差異量表，測量三組照片在136位使用者的答案 中，是否能吻合先前提出的強度-偏向模型。 實驗結果發現，我們的方法和google image回傳的結果類似， 使用者問卷調查結果支持我們的方法對於正負偏向的判定，且比 google有更佳的強弱分離程度。 zh_TW dc.description.abstract (摘要) This study attempts to proceed from psychology to explore the emotional state of the classification method described why, in order to be emotional and semantic links, images as we try to stimulate the emotional state of the source, the Internet community for sharing Flickr content sampling and observation, using basic psychological research in terms of mood changes with the parts of speech, with word labels extracted 12,000 photos, label and classification of words and word co-occurrence of emotional computing, computing association rules. At the same time, through the semantic differential scale, tend to put forward a new classification of the coordinates and intensity. Through the frequency threshold filter, filling part of speech combined with the terms of the method stems from the 65,983 non-duplicate text labels, the last 272 to get things with the concept of emotional bias term, and positive and negative emotions tend to association rules. In order to verify these words through images is to bring people`s emotional state associated with our pipeline through the three sources: Flickr , google image , and photos through our index labels: the proportion of emotional words, the community filtering parameters to select the final 42 photos to compare. Through the semantic differential scale, measuring three photos in 136 users of answers, whether the agreement made earlier strength - bias model. Experimental results showed that our methods and google image similar to the results returned, the user survey results support our approach to determine the positive and negative bias, and the strength of better than google degree of separation. en_US dc.description.tableofcontents 第一章 緒論..................................................................................................................9 1.1 情緒的定義.......................................................................................................10 1.2 情緒表達...........................................................................................................11 1.3 情緒研究的重要性...........................................................................................11 1.4 動機與目的.......................................................................................................12 第二章 領域知識與相關研究....................................................................................13 2.1 基礎情緒分類...................................................................................................13 2.1.1 心理學對於情緒的歸納與分類................................................................13 2.1.2 透過語料和專家方法進行情緒字詞分類................................................16 2.2 詞意相似度 - 字詞共現計算...........................................................................17 2.2.1 字詞共現指標 (tag co-occurrence index)................................................17 2.2.2 點式交互資訊 (point-wise mutual information) ....................................18 2.2.3 關聯規則演算法 (Apriori Algorithm)......................................................19 2.3 詞幹 (Stemming)..............................................................................................20 2.4 語意差異量表 (Semantic Differential Scale)..................................................21 2.5 影像與情緒.......................................................................................................22 2.6 網路社群作為語料來源...................................................................................24 2.7 小結...................................................................................................................25 第三章 資料分析與模型建立....................................................................................27 3.1 研究架構...........................................................................................................27 i 3.1.1 資料來源 ..................................................................................................27 3.1.1.1 Flickr攝影社群.......................................................................................28 3.1.1.2 決定情緒類別.........................................................................................29 3.1.1.3 Flickr API................................................................................................33 3.1.2 資料前處理................................................................................................33 3.1.2.1 雜訊.........................................................................................................33 3.1.2.3 字詞頻率.................................................................................................34 3.1.2.4 過濾門檻.................................................................................................35 3.1.2.5 詞性標記 POS.......................................................................................35 3.1.3 Stemming by Porter Stemmer....................................................................35 3.1.4 字詞共現計算 ..........................................................................................36 3.1.4.1 兩字詞之關聯：PMI.............................................................................36 3.1.4.2 兩字詞以上之關聯：apriori algorithm.................................................41 3.1.5 文字標籤隱含的情緒偏向，以強度與偏向分類....................................42 3.1.6 四象限的事物概念字詞與情緒關聯........................................................44 3.2 前測問卷與VA model調整：強度-偏向座標..................................................46 3.3 資料庫建置.......................................................................................................47 3.4 決定帶有情緒影像的候選照片.......................................................................49 3.5 圖片情緒偏向排序，以社群參數進行過濾...................................................49 ii 3.6 小結...................................................................................................................50 第四章 實驗結果與評估............................................................................................52 4.1 抽樣...................................................................................................................53 4.1.1 基礎情緒字詞選取與排名抽樣結果........................................................53 4.1.2 考慮詞性變化的抽樣結果........................................................................55 4.2 字詞頻率 tag frequency...................................................................................59 4.2.1 挑選詞頻過濾門檻....................................................................................61 4.2.2 stemming....................................................................................................62 4.3 挑選候選照片...................................................................................................63 4.4照片中標籤字詞分析........................................................................................77 4.4.1縮小範圍、凸顯主題.................................................................................78 4.4.2字詞變化合併.............................................................................................78 4.4.3主流語系.....................................................................................................79 4.4.4 與主題相關、感受性的標籤會被保留....................................................79 4.5 小結...................................................................................................................80 第五章 問卷評估與實驗結果....................................................................................82 5.1 問卷結果總覽...................................................................................................82 5.1.1 分類結果一覽：強度................................................................................83 5.1.2 分類結果一覽：偏向................................................................................84 5.1.3 強度與偏向總覽........................................................................................84 5.3 研究限制...........................................................................................................87 第六章 結論與未來研究............................................................................................89 6.1 研究成果...........................................................................................................89 iii 6.1.1 影像中字詞共現的方法，可得到事物概念與情緒字詞的關聯............89 6.1.2 透過問卷提出新的分類強度-偏向分類模型..........................................89 6.2 以圖像作為情緒引發來源，評估使用者的主觀解讀與反應.......................90 6.2.1 引發情緒偏向的觀察................................................................................91 6.2.2 引發情緒強弱的內容觀察........................................................................91 6.2.3 高頻詞組對於情緒的關聯強度較不明顯................................................91 6.3 未來研究...........................................................................................................92 6.3.1 影像中的語意探索....................................................................................92 6.3.2 情緒詞分類模型的發展............................................................................92 6.3.3 問卷抽樣的照片來源與數量....................................................................92 6.3.4 圖像中的符號意義：................................................................................93 參考文獻......................................................................................................................94 附錄A 高頻字詞的PMI值...........................................................................................98 附錄B問卷圖片與分析.............................................................................................106 附錄D問卷結果.........................................................................................................163 附錄D：情緒與字詞概念關聯研究 前測問卷：...................................................180 附錄E：前測問卷強度平均值.................................................................................184 附錄F：前測問卷偏向值，以100為滿分................................................................185 附錄G：語意量表結果調整過後的偏向-強度model..............................................186 zh_TW dc.format.extent 13573282 bytes - dc.format.mimetype application/pdf - dc.language.iso en_US - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0095753015 en_US dc.subject (關鍵詞) 情緒分類 zh_TW dc.subject (關鍵詞) 情緒檢索 zh_TW dc.subject (關鍵詞) 情緒詞 zh_TW dc.subject (關鍵詞) 社群網路 zh_TW dc.subject (關鍵詞) 字詞共現 zh_TW dc.subject (關鍵詞) 關聯 規則 zh_TW dc.subject (關鍵詞) 影像與情緒 zh_TW dc.subject (關鍵詞) sentiment classification en_US dc.subject (關鍵詞) sentiment retrieval en_US dc.subject (關鍵詞) sentiment words en_US dc.subject (關鍵詞) word co-occurrence en_US dc.subject (關鍵詞) association rules en_US dc.subject (關鍵詞) image and emotion en_US dc.subject (關鍵詞) social network en_US dc.title (題名) 透過圖片標籤觀察情緒字詞與事物概念之關聯 zh_TW dc.title (題名) An analysis on association between emotion words and concept words based on image tags en_US dc.type (資料類型) thesis en dc.relation.reference (參考文獻) [1] J. Darley, S. Glucksberg, R. Kinchla ,Psychology , Prentice Hall College Div.5th edition ,1991. [2] E. Fox, Emotion Science： Cognitive and Neuroscientific Approaches to Understanding Human Emotions. Palgrave Macmillan, Sep. 2008. [3] R. W. Picard, E. Vyzas, and J. Healey, "Toward machine emotional intelligence： Analysis of affective physiological state", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1175-1191, Oct. 2001. [4] R. W. Picard, Affective computing. The MIT Press, 1997. [5] P Shaver, J Schwartz, D Kirson, `` Emotion knowledge： Further exploration of a prototype approach``. Journal of Personality and Social Psychology, Vol 52(6), 1061- 1086, 1987. [6] MJ. Power, T. Dalgleish, Cognition and emotion. From order to disorder. Hove, East Sussex, UK： Psychology Press, 1997. [7] C.E. Izard, The Psychology of Emotions, New York, London： Plenum Press, 1991 [8] J.A. Russell, “A circumplex model of affect”. Journal of Personality and Social Psychology, 39(6)：1161-1178, 1980. [9] J. Posner, J. A. Russell, and B. S. Peterson, "The circumplex model of affect： An integrative approach to affective neuroscience, cognitive development, and psychopathology", Development and Psychopathology, vol. 17, no. 03, pp. 715-734, 2005. 86 ‧ 國 立 政 治 大 學 ‧ N a t i on a l Ch e n g c h i U n i v e r s i t y [10] R. Valitutti, "WordNet-affect：an affective extension of WordNet". Proceedings of the 4th International Conference on Language Resources and Evaluation, vol. 2004, pp. 1083-1086, 2004. [11] B. Sigurbjörnsson and R. van Zwol, "Flickr tag recommendation based on collective knowledge". Proceeding of the 17th international conference on World Wide Web, ser. WWW `08. New York, NY, USA： ACM, pp. 327-336, 2008. [12] R. Jonathon Read, “Recognising affect in text using pointwise-mutual information”. master degree thesis ,University of Sussex , 2004. [13] R. Agrawal and R. Srikant, "Fast algorithms for mining association rules". Proc. 20th Int. Conf. Very Large Data Bases, VLDB, pp. 487-499, 1994. [14] M. F. Porter, "An algorithm for suffix stripping". Program, vol. 14, no. 3, pp. 130-137, 1980. [15] D. A. Hull, "Stemming algorithms： A case study for detailed evaluation". Journal of the American Society for Information Science, vol. 47, no. 1, pp. 70-84, Dec. 1998. [16] J. Xu and B. W. Croft, "Corpus-Based stemming using cooccurrence of word variants". ACM Transactions on Information Systems, vol. 16, no. 1, pp. 61-81, 1998. [17] C. E. Osgood, "Semantic differential technique in the comparative study of cultures1," American Anthropologist, vol. 66, no. 3, pp. 171-200, 1964. [18] J. Berger , Ways of Seeing. Penguin ,1972 . [19] S. Schmidt and W. G. Stock, "Collective indexing of emotions in images. a study in emotional information retrieval", Journal of the American Society for Information Science and Technology, vol. 60, no. 5, pp. 863-876, 2009. [20] J. San Pedro and S. Siersdorfer, "Ranking and classifying attractiveness of photos in 87 ‧ 國 立 政 治 大 學 ‧ N a t i on a l Ch e n g c h i U n i v e r s i t y folksonomies”. Proceedings of the 18th international conference on World wide web, ser. WWW `09. New York, NY, USA： ACM, pp. 771-780, 2009. [21] J. Beaudoin, "Folksonomies： Flickr image tagging： Patterns made visible". Bul. Am. Soc. Info. Sci. Tech., vol. 34, no. 1, pp. 26-29, 2007. [22]鄭學侖，「以web2.0民眾分類法建置音樂推薦系統之研究」，國立政治大學資訊 管理研究所碩士論文。 [23] A.J. Gill, D.Gergle, R.M. French, and J.Oberlander, "Emotion rating from short blog texts", Proceeding of the twenty-sixth annual SIGCHI conference on Human factors in computing systems, ser. CHI `08. New York, NY, USA： ACM, pp. 1121-1124, 2008. [24] E. Zheleva, J. Guiver, E. M. Rodrigues, and N. M. Frayling, "Statistical models of music-listening sessions in social media", Proceedings of the 19th international conference on World wide web, ser. WWW `10. New York, NY, USA： ACM, pp. 1019- 1028, 2010. [25] S. Siersdorfer, E. Minack, F. Deng, and J. Hare, "Analyzing and predicting sentiment of images on the social web". Proceedings of the international conference on Multimedia, ser. MM `10. New York, NY, USA： ACM, pp. 715-718, 2010. [26] G.Grefenstette , “Comparing the Language Used in Flickr, General Web Pages, Yahoo Images and Wikipedia”. LREC08 proceedings, 6-11, 2008. [27] L. Kennedy, M. Naaman, S. Ahern, R. Nair, and T. Rattenbury, "How Flickr helps us make sense of the world： context and content in community-contributed media collections". Proceedings of the 15th international conference on Multimedia, ser. MULTIMEDIA `07. New York, NY, USA： ACM, pp. 631-640, 2007. [28] C. Marlow, M. Naaman, D. Boyd, and M. Davis, "HT06, tagging paper, taxonomy, 88 ‧ 國 立 政 治 大 學 ‧ N a t i on a l Ch e n g c h i U n i v e r s i t y Flickr, academic article, to read". Proceedings of the seventeenth conference on Hypertext and hypermedia, ser. HYPERTEXT `06. New York, NY, USA： ACM, pp. 31- 40, 2006. [29] G. Begelman, "Automated tag clustering： Improving search and exploration in the tag space". Proceeding of the Collaborative Web Tagging Workshop at WWW`06, 2006. [30] 吳筱玫、周芷伊，「Tagging的分類與知識意涵：以Flickr首頁圖片為例」，新聞學 研究，台北，2009年4月，頁265-305 [31] Mikels, J. A., Fredrickson, B. L., Larkin, G. R., Lindberg, C. M., Maglio, S. J., and Reuter-Lorenz, P. A. (2005). Emotional category data on images from the international affective picture system. Behavior Research Methods, 37(4):626-630. [32] Lang, P. J. (1995). The emotion probe. studies of motivation and attention. The American psychologist, 50(5):372-385. [33] Peter Mika. (2007). “Ontologies are us: emergent semantics in folksonomy systems In Social Networks and the Semantic Web”. International Semantic Web Conference, International Semantic Web Conference (ISWC2005), Vol. 5, No. 1. (March 2007), pp. 5-15 zh_TW
