Library and Information Service >
Research on Image Emotional Annotations Based on Social Tags
Received date: 2016-06-30
Revised date: 2016-10-20
Online published: 2016-11-05
[Purpose/significance] To index emotion type of images is useful for organizing and searching images by affective clues.[Method/process] With the Flickr images, this paper took the algorithm of Pointwise Mutual Information and WordNet-Affect wordlists, dealing with tags to categorize images based on Ekman's six emotion types. Then it conducted experiments to test the results. Finally, it discussed the influence of images' features, indexing motivations and the number of non-affect tags on indexing results.[Result/conclusion] Findings indicated for one image, the non-affective tags and affective tags reflected the similar emotion as the whole image.And the typical affective wordlists were also tested useful than before. Moreover, the categorizing results based on typical affective wordlists were accorded with the results categorizing by users. Among 6 emotion types, the majority of Happy and Sad images were categorized correctly. While the Surprise images were categorized worst. Furthermore, the accuracy of categorizing was related to the typicality and unique of emotions of images, the difference between images uploaders and users, and the numbers of non-affective tags in images.
Key words： image; social labeling; emotional annotations; PMI algorithm
Song Lingchao , Huang Kun . Research on Image Emotional Annotations Based on Social Tags[J]. Library and Information Service, 2016 , 60(21) : 103 -112 . DOI: 10.13266/j.issn.0252-3116.2016.21.014
[1] 黄崑,骆方,游祎. 图像情感特征及其检索应用[J]. 情报科学,2010,28(4):602-606.
[2] 陆泉,丁恒. 基于情感的图像检索研究综述[J]. 情报理论与实践,2013,36(2):119-124.
[3] 高彦宇,王新平,尹怡欣.自然风景图像情感标识方法研究.小型微型计算机系统,2011,4(4):767-771.
[4] SHIN Y, KIM E Y.Affective prediction in photographic images using probabilistic affective model[C]//Proceedings of the ACM international conference on image and video retrieval.Xi'an:ACM,2010:390-397.
[5] 王上飞,薛佳,王煦法. 基于内容的情感图像获取模型[J]. 计算机科学,2004,31(9):186-190.
[6] 黄崑. 情感信息处理研究综述[J]. 现代图书情报技术,2007(11):67-71.
[7] ULINSKI M, SOTO V, HIRSCHBERG J. Finding emotion in image descriptions[C/OL].[2016-03-06].http://dl.acm.org/citation.cfm?id=2346684.
[8] 宋相法,焦李成. 基于稀疏表示的多示例图像分类[J]. 计算机科学,2015,42(1):293-296.
[9] 王澍,吕学强,张凯,等. 基于快速鲁棒特征集合统计特征的图像分类方法[J]. 计算机应用,2015,35(1):224-230.
[10] 李海芳,贺静,焦丽鹏. 基于颜色特征的图像情感分类[J]. 计算机应用,2007,27(2):453-455.
[11] 陆泉,陈静,丁恒. 基于社会标签的图像情感自动分类标注研究[J]. 图书情报工作,2014,58(12):118-123.
[12] 夏召强. 面向互联网社会化图像的标签优化算法研究[D].西安:西北工业大学,2014.
[13] 王琪,杜娟,程彬,等. 基于协作式标注图像数据的垃圾标签检测方法[J]. 计算机与现代化,2015(6):41-45.
[14] WANG H, HUANG H, DING C. Image annotation using bi-relational graph of images and semantic labels[C]//2011 IEEE conference on computer vision and pattern recognition(CVPR).Colorado Springs:IEEE, 2011:793-800.
[15] 田枫,沈旭昆.一种适合弱标签数据集的图像语义标注方法[J]. 软件学报,2013,24(10):2405-2418.
[16] JIN Y, KHAN L, WANG L, et al. Image annotations by combining multiple evidence &wordNet.[C]//ACM International Conference on Multimedia.Singapore:ACM,2005:706-715.
[17] HU M, LIU B. Mining and summarizing customer reviews[C]//Proceedings of the tenth ACM SIGKDD international conference on knowledge discovery and data mining. Seattle:ACM, 2004:168-177.
[18] WU Y, REN F. Improving emotion recognition from text with fractionation training[C]//2010 International conference on natural language processing and knowledge engineering. Beijing:IEEE, 2010:1-7.
[19] GHAZI D, INKPEN D,et al. Hierarchical approach to emotion recognition and classification in texts[C]//Canadian conference on artificial intelligence. Berlin:Springer, 2010:40-50.
[20] ALM C O, ROTH D, SPROAT R. Emotions from text:machine learning for text-based emotion prediction[C]//Proceedings of the conference on human language technology and empirical methods in natural language processing. Vancouver:Association for computational linguistics, 2005:579-586.
[21] SHELKE M N M. Approaches of emotion detection from text[J].International journal of computer science and information technology research, 2014, 2(2):123-128.
[22] AGRAWAL A, AN A. Unsupervised emotion detection from text using semantic and syntactic relations[C]//2012 IEEE/WIC/ACM International Conferences on Web intelligence and intelligent agent technology. Macau:IEEE, 2012:346-353.
[23] SHAHEEN S, EL-HAJJ W, HAJJ H, et al. Emotion recognition from text based on automatically generated rules[C]//2014 IEEE international conference on data mining workshop. Shenzhen:IEEE, 2014:383-392.
[24] HATZIVASSILOGLOU V, MCKEOWN K R.Predicting the semantic orientation of adjectives[C]//Proceedings of the 35th annual meeting of the Association for Computational Linguistics.Madrid:Association for Computational Linguistics, 1997:174-181.
[25] KULLIN H.Flickr reaches 5 billion photos[EB/OL].[2015-04-28].http://www.kullin.net/2010/09/flickr-5-billion-photos/.
[26] ICMR-ACM international conference on multimedia retrieval[EB/OL].[2015-11-02].http://press.liacs.nl/mirflickr/mirdownload.html.
[27] STRAPPARAVA C, MIHALCEA R. Learning to identify emotions in text[C]//Proceedings of the 2008 ACM symposium on applied computing. Fortalez:ACM, 2008:1556-1560.
[28] CHURCH K W, HANKS P. Word association norms, mutual information, and lexicography[J]. Computational linguistics, 1990,16(1):22-29.
[29] RECCHIA G, JONES M N. More data trumps smarter algorithms:comparing pointwise mutual information with latent semantic analysis[J]. Behavior research methods, 2009, 41(3):647-656.
[30] 杜锐,朱艳辉,田海龙,等. 基于平滑SO-PMI算法的微博情感词典构建方法研究[J]. 湖南工业大学学报,2015(5):77-81.
[31] 赵黎光. 基于依存句法的句子级细粒度情感计算[D].广州:华南理工大学,2015.
[32] SIGURBJORNSSON B, VAN ZWOL R. Flickr tag recommendation based on collective knowledge[C]//Proceedings of the 17th international conference on World Wide Web. Beijing:ACM, 2008:327-336. 作者贡献说明:宋灵超:负责设计算法、收集并处理实验数据,进行数据分析,撰写论文初稿; 黄崑:进行研究设计,撰写数据讨论部分,进行全文修改和润色。
/
| 〈 |
|
〉 |
