Research on Image Emotional Tag Generation Mechanism Based on the “Cloud Pet Keeping” Phenomenon

  • Chen Tang
  • Ke Zhong
  • Liqun ZhangEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10920)


In Chinese UGC background, the “Cloud Pet Keeping” phenomenon that social media users keep eyes on certain pets’ growth by viewing the photos and texts released by pet bloggers is rising. Users obtain emotional resonance through browsing pet photos shared and are happy to contribute the consuming behavior. However, there are still large amount of people can’t find their favorite pets through searching. The emotional tags’ lack can be a possible reason, which causes the bad user experience. This research tried to purpose an approach based on “cloud pet keeping” phenomenon by using neural networks to develop the image emotional tag generation mechanism. In this experiment, cats’ photos are taken as the example to construct the model. This mechanism is used to predict the emotional categories of images. When users uploading the images, the mechanism will automatically generate emotional tags based on its prediction. This is a positive way to solve the problem in the lack of image emotional tags. It is foreseeable that the theory can be applied to other fields, such as industrial product and so on.


Image emotional tags Neural network “Cloud pet keeping” phenomenon 


  1. 1.
    Daugherty, T., Eastin, M.S., Bright, L.: Exploring consumer motivations for creating user-generated content. J. Interact. Advert. 8(2), 16–25 (2008)CrossRefGoogle Scholar
  2. 2.
    Liang, N., Zhong, J., Wang, D., Zhang, L.: The Exploration of user knowledge architecture based on mining user generated contents – an application case of photo-sharing website. In: Marcus, A. (ed.) DUXU 2016. LNCS, vol. 9748, pp. 180–192. Springer, Cham (2016). Scholar
  3. 3.
    Wang, D., Liang, N., Zhong, J., Zhang, L.: Mining and construction of user experience content: an approach of feature analysis based on image. In: Marcus, A. (ed.) DUXU 2016. LNCS, vol. 9748, pp. 223–234. Springer, Cham (2016). Scholar
  4. 4.
    Xie, M., Zhang, L., Liang, T.: A Quantitative study of emotional experience of Daqi based on cognitive integration. In: Marcus, A., Wang, W. (eds.) DUXU 2017. LNCS, vol. 10288, pp. 306–323. Springer, Cham (2017). Scholar
  5. 5.
    Liang, T., Zhang, L., Xie, M.: Research on image emotional semantic retrieval mechanism based on cognitive quantification model. In: Marcus, A., Wang, W. (eds.) DUXU 2017. LNCS, vol. 10290, pp. 115–128. Springer, Cham (2017). Scholar
  6. 6.
    Zhong, J., Wang, D., Liang, N., Zhang, L.: Research on user experience driven product architecture of smart device. In: Marcus, A. (ed.) DUXU 2016. LNCS, vol. 9748, pp. 425–434. Springer, Cham (2016). Scholar
  7. 7.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)CrossRefGoogle Scholar
  8. 8.
    Johnson, S.: Stephen Johnson on Digital Photography. O’Reilly, Sebastopol (2006). ISBN 0-596-52370-XGoogle Scholar
  9. 9.
    邓铸, 朱晓红. 心理统计学与SPSS应用[M]. 华东师范大学出版社 (2009)Google Scholar
  10. 10.
    Poynton, C.: The Magnitude of Nonconstant Luminance Errors in Charles Poynton, A Technical Introduction to Digital Video. WIley, New York (1996)Google Scholar
  11. 11.
    Fox, E.: Emotion Science Cognitive and Neuroscientific Approaches to Understanding Human Emotions. Palgrave Macmillan, Basingstoke (2008)Google Scholar
  12. 12.
    Carstensen, L.L., Pasupathi, M., Mayr, U., Nesselroade, J.R.: Emotional experience in everyday life across the adult life span. J. Personal. Soc. Psychol. 79, 644 (2000)CrossRefGoogle Scholar
  13. 13.
    Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning (2017)Google Scholar
  14. 14.
    Vasconcelos, C.N., Vasconcelos, B.N.: Increasing deep learning melanoma classification by classical and expert knowledge based image transforms. CoRR, abs/1702.07025 (2017)Google Scholar
  15. 15.
    Marchesi, M.: Megapixel size image creation using generative adversarial networks. ArXiv e-prints, May 2017Google Scholar
  16. 16.
    Xu, Y., Jia, R., Mou, L., Li, G., Chen, Y., Lu, Y., Jin, Z.: Improved relation classification by deep recurrent neural networks with data augmentation. CoRR, abs/1601.03651 (2016)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Institute of Design ManagementShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations