International Journal of Business Analytics and Intelligence

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Visual Sentiment Exploration of Customer Emotions using Image Analytics


Affiliations
1 City University College of Ajman, Ajman, United Arab Emirates
     

   Subscribe/Renew Journal


Sentiment analysis is one of the vital areas to evaluate customer emotions. The growing prominence of sentiment analysis is because of social network platforms, which companies use for 360-degree consumer feedback. Companies use sentiment analysis as an automated process of recognising positive and negative emotions in online text data. By examining sentiments in social media comments and reviews, businesses can better understand how customers feel about their brands and products. Visual sentiment analysis aims to understand how images affect people in terms of evoked emotions. Companies are exposed to consumers’ images on social media by consumers, and they need image analytics for social listening and response. In this paper, we took 21 random pictures from social media to identify the visual sentiment analysis. We use the image embedding algorithm in Inception V3, and Liu Hu and Ekman Algorithm to calculate the outcomes’ polarity. Further, we used the machine learning classification algorithm to identify which model does the accurate classification of evoked emotions as happy and sad. Classification algorithms are based on the 2,048 features generated by the Inception V3 algorithm, and evoked emotions are classified accordingly.

Keywords

Inception V3, Liu Hu Algorithm, Ekman Polarity, Image Analytics, Picture Polarity, Naïve Bayes, Support Vector Machine, Neural Networks, Random Forest.
Subscription Login to verify subscription
User
Notifications
Font Size


  • Alam, F., Imran, M., & Ofli, F. (2017). Image4Act: Online social media image processing for disaster response. Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017 – ASONAM ‘17, pp. 601-604. doi:https://doi.org/10.1145/3110025.3110164

  • Almgren, K., Kim, M., & Lee, J. (2017). Mining social media data using topological data analysis. 2017 IEEE International Conference on Information Reuse and Integration (IRI), pp. 144-153. doi:https://doi.org/10.1109/IRI.2017.41

  • Amato, G., Bolettieri, P., Monteiro de Lira, V., Muntean, C. I., Perego, R., & Renso, C. (2017). Social media image recognition for food trend analysis. Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1333-1336. doi:https://doi.org/10.1145/3077136.3084142

  • Appel, G., Grewal, L., Hadi, R., & Stephen, A. T. (2019). The future of social media in marketing. Journal of the Academy of Marketing Science. doi:https://doi.org/10.1007/s11747-019-00695-1

  • Bakhshi, S., Shamma, D. A., & Gilbert, E. (2014). Faces engage us: Photos with faces attract more likes and comments on Instagram. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 965-974. doi:https://doi.org/10.1145/2556288.2557403

  • Basnyat, B., Anam, A., Singh, N., Gangopadhyay, A., & Roy, N. (2017). Analyzing social media texts and images to assess the impact of flash floods in cities. 2017 IEEE International Conference on Smart Computing (SMARTCOMP), pp. 1-6. doi:https://doi.org/10.1109/SMARTCOMP.2017.7946987

  • Castiglione, A., Cattaneo, G., & De Santis, A. (2011). A forensic analysis of images on online social networks. 2011 Third International Conference on Intelligent Networking and Collaborative Systems, pp. 679-684. doi:https://doi.org/10.1109/INCoS.2011.17

  • Corliss, R. (2019). Photos on Facebook generate 53% more likes than the average post [New Data]. Retrieved October 23, 2019, from https://blog.hubspot.com/blog/tabid/6307/bid/33800/photos-on-facebook-generate-53-more-likes-than-the-average-post-new-data.aspx

  • Garimella, V. R. K., Alfayad, A., & Weber, I. (2016). Social media image analysis for public health. Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, pp. 5543-5547. doi:https://doi.org/10.1145/2858036.2858234

  • Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 168-177. doi:https:// doi.org/10.1145/1014052.1014073

  • Hu, N., Bose, I., Koh, N. S., & Liu, L. (2012). Manipulation of online reviews: An analysis of ratings, readability, and sentiments. Decision Support Systems, 52(3), 674-684. https://doi.org/10.1016/j.dss.2011.11.002

  • Hu, X., Tang, L., Tang, J., & Liu, H. (2013). Exploiting social relations for sentiment analysis ACM International Conference on Web Search and Data Mining, pp. 537-546. doi:https://doi.org/10.1145/2433396.2433465

  • Islam, J., & Zhang, Y. (2016). Visual sentiment analysis for social images using transfer learning approach. 2016 IEEE International Conferences on Big Data and Cloud Computing (BDCloud), Social Computing and Networking (SocialCom), Sustainable Computing and Communications (SustainCom) (BDCloud-SocialCom-SustainCom), pp. 124-130. doi:https://doi.org/10.1109/BDCloud -SocialCom-SustainCom.2016.29

  • Ji, R., Cao, D., Zhou, Y., & Chen, F. (2016). Survey of visual sentiment prediction for social media analysis. Frontiers of Computer Science, 10(4), 602-611. doi:https://doi.org/10.1007/s11704-016-5453-2

  • Maigrot, C., Kijak, E., & Claveau, V. (2018). Contextaware forgery localization in social-media images: a feature-based approach evaluation. 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 545-549. doi:https://doi.org/10.1109/ICIP.2018.8451726

  • Mantyla, M. V., Novielli, N., Lanubile, F., Claes, M., & Kuutila, M. (2017, May). Bootstrapping a Lexicon for Emotional Arousal in Software Engineering, pp. 198-202. doi:https://doi.org/10.1109/MSR.2017.47

  • Pittman, M., & Reich, B. (2016). Social media and loneliness: Why an Instagram picture may be worth more than a thousand Twitter words. Computers in Human Behavior, 62, 155-167. doi:https://doi.org/10.1016/j.chb.2016.03.084

  • Tsang, S.-H. (2015). Inception-v3—1st Runner Up (Image Classification) in ILSVRC 2015. Retrieved from https://medium.com/@sh.tsang/review-inception-v3-1st-runner-up-image-classification-in-ilsvrc-2015-17915421f77c

  • Wang, W., Li, Y., Huang, Y., Liu, H., & Zhang, T. (2017). A method for identifying the mood states of social network users based on cyber psychometrics. Future Internet, 9(2), 22. doi:https://doi.org/10.3390/fi9020022

  • Wang, Y., & Li, B. (2015). Sentiment Analysis for Social Media Images. 2015 IEEE International Conference on Data Mining Workshop (ICDMW), 1584-1591. https://doi.org/10.1109/ICDMW.2015.142

  • Webster. (2015). 8 Surprising Twitter Statistics to Get More Engagement [Postcron]. Retrieved from Postcron—Social Media Marketing Blog and Digital Marketing Blog

  • https://postcron.com/en/blog/8surprising-twitter-statistics-get-more-engagement/


Abstract Views: 96

PDF Views: 0




  • Visual Sentiment Exploration of Customer Emotions using Image Analytics

Abstract Views: 96  |  PDF Views: 0

Authors

Riktesh Srivastava
City University College of Ajman, Ajman, United Arab Emirates

Abstract


Sentiment analysis is one of the vital areas to evaluate customer emotions. The growing prominence of sentiment analysis is because of social network platforms, which companies use for 360-degree consumer feedback. Companies use sentiment analysis as an automated process of recognising positive and negative emotions in online text data. By examining sentiments in social media comments and reviews, businesses can better understand how customers feel about their brands and products. Visual sentiment analysis aims to understand how images affect people in terms of evoked emotions. Companies are exposed to consumers’ images on social media by consumers, and they need image analytics for social listening and response. In this paper, we took 21 random pictures from social media to identify the visual sentiment analysis. We use the image embedding algorithm in Inception V3, and Liu Hu and Ekman Algorithm to calculate the outcomes’ polarity. Further, we used the machine learning classification algorithm to identify which model does the accurate classification of evoked emotions as happy and sad. Classification algorithms are based on the 2,048 features generated by the Inception V3 algorithm, and evoked emotions are classified accordingly.

Keywords


Inception V3, Liu Hu Algorithm, Ekman Polarity, Image Analytics, Picture Polarity, Naïve Bayes, Support Vector Machine, Neural Networks, Random Forest.

References