AI helps you reading Science
AI Insight
AI extracts a summary of this paper
Weibo:
How Do Your Friends On Social Media Disclose Your Emotions?
PROCEEDINGS OF THE TWENTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, pp.306-312, (2014)
EI
Keywords
Abstract
Extracting emotions from images has attracted much interest, in particular with the rapid development of social networks. The emotional impact is very important for understanding the intrinsic meanings of images. Despite many studies having been done, most existing methods focus on image content, but ignore the emotion of the user who pub...More
Code:
Data:
Introduction
- People use colorful images to express their happiness, while gloomy images are used to express sadness.
- With the rapid development of online social networks, e.g., Flickr 1 and instagram 2, more and more people like to share their daily emotional experiences using these platforms.
- The authors' preliminary statistics indicate that more than 38% of the images on Flickr are explicitly annotated with either positive or negative emotions.
- In online social networks such as Flickr and Instagram, posting discussions on a shared image is becoming common.
- On Flickr, when a user publishes an image, on average 7.5 friends will leave comments (when users follow each other on Flickr, the authors say they
Highlights
- Image is a natural way to express one’s emotions
- To address the above challenges, we propose a novel emotion learning model to integrate both the image content and the corresponding comments
- We propose an emotion learning method, which bridges the image and comment information by utilizing a latent space
- Can friends’ interactions help us better understand one’s emotions? In this paper, we propose a novel emotion learning method, which models the comment information and visual features of images simultaneously by learning a latent space to bridge these two pieces of information
- Experiments on a Flickr dataset demonstrates that our model improves the performance on inferring users’ emotions +37.4%
Methods
- LDA+SVM EL+SVM SVM PFG LDA+SVM EL+SVM SVM PFG LDA+SVM EL+SVM SVM.
- 0.337 0.312 0.324 Disgust PFG LDA+SVM EL+SVM Fear.
- 0.191 0.142 0.163 Sadness F 1 F 1 −Comments −Tie
Results
- The dataset, all codes, and visual features used in the experiments are public available 3.
Conclusion
- The authors propose a novel emotion learning method, which models the comment information and visual features of images simultaneously by learning a latent space to bridge these two pieces of information.
- Can friends’ interactions help them better understand one’s emotions?
- Experiments on a Flickr dataset demonstrates that the model improves the performance on inferring users’ emotions +37.4%
Tables
- Table1: Notations in the proposed model
- Table2: Performance of emotion inference. Precision Recall F1-score Emotion Method
- Table3: Image interpretations. We demonstrate how each visual feature distributes over each category of images by μet learned by the proposed model. The visual features include saturation (SR), saturation contrast (SRC), bright contrast (BRC), cool color ratio (CCR), figure-ground color difference (FGC), figure-ground area difference (FGA), background texture complexity (BTC), and foreground texture complexity (FTC). We also show a user’s friends response after the user publishes different categories of images
Funding
- The work is supported by the National High-tech R&D Program (No 2014AA015103), National Basic Research Program of China (No 2011CB302201, No 2014CB340500), Natural Science Foundation of China (No 61222212)
Reference
- Abramowitz, M., and Stegun, I. 1970. Handbook of mathematical functions.
- Bernardo, J. M., and Smith, A. F. 2009. Bayesian theory, volume 405. Wiley. com.
- Blei, D. M.; Ng, A. Y.; and Jordan, M. I. 200Latent dirichlet allocation. JMLR 3:993–1022.
- Burges, C. J. 1998. A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery 2(2):121–167.
- Chang, C.-C., and Lin, C.-J. 2011. LIBSVM: A library for support vector machines. ACM TIST 2:27:1–27:27.
- Christophe, V., and Rime, B. 1997. Exposure to the social sharing of emotion: Emotional impact, listener responses and secondary social sharing. European Journal of Social Psychology 27(1):37–54.
- Elguebaly, T., and Bouguila, N. 2011. Bayesian learning of finite generalized gaussian mixture models on images. Signal Processing 91(4):801–820.
- Heinrich, G. 2005. Parameter estimation for text analysis. Web: http://www.arbylon.net/publications/text-est.pdf.
- Jaakkola, T. S., and Qi, Y. 2006. Parameter expanded variational bayesian methods. In NIPS’06, 1097–1104.
- Jia, J.; Wu, S.; Wang, X.; Hu, P.; Cai, L.; and Tang, J. 2012. Can we understand van gogh’s mood?: learning to infer affects from images in social networks. In ACM Multimedia 2012, 857–860.
- Jordan, M. I. 1999. An introduction to variational methods for graphical models. In Machine Learning, 183–233.
- Lee, P. M. 20Bayesian statistics: an introduction. John Wiley & Sons.
- Moll, J.; de Oliveira-Souza, R.; Moll, F. T.; Ignacio, F. A.; Bramati, I. E.; Caparelli-Daquer, E. M.; and Eslinger, P. J. 2005. The moral affiliations of disgust: A functional mri study. Cognitive and behavioral neurology 18(1):68–78.
- Murphy, K. P. 2007. Conjugate bayesian analysis of the gaussian distribution. def 1(2σ2):16.
- Ou, L.-C.; Luo, M. R.; Woodcock, A.; and Wright, A. 2004. A study of colour emotion and colour preference. part i: Colour emotions for single colours. Color Research & Application 29(3):232–240.
- Resnik, P., and Hardisty, E. 2010. Gibbs sampling for the uninitiated. Technical report, DTIC Document.
- Rime, B. 2005. Le partage social des emotions. Presses universitaires de France.
- Shin, Y., and Kim, E. Y. 2010. Affective prediction in photographic images using probabilistic affective model. In CIVR’10, 390–397.
- Tang, W.; Zhuang, H.; and Tang, J. 2011. Learning to infer social ties in large networks. In ECML/PKDD (3)’11, 381– 397.
- Wainwright, M., and Jordan, M. 2008. Graphical models, exponential families, and variational inference. Foundations and Trends in Machine Learning 1(1-2):1–305.
Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn