Visual Sentiments Analysis Using Deep Learning
Bilal Ahmad1*, Rozia Perviaz2, Afifa Qureshi2, Syed Mohsin Shah2 and Mudassir Riaz1
1School Of Computer Science and Engineering, Central South University, Lushan Road Changsha, China
2Department of Computer Science, Mohi-Ud-Din Islamic University, Nearian Sharif Azad, Jamu Kashmir, India
*Corresponding Author: Bilal Ahmad, School of Computer Science and
Engineering, Central South University, Lushan Road Changsha, China.
April 17, 2023; Published: June 23, 2023
Social networking is a potent way for individuals to express their ideas and emotions on a specific subject, allowing others to gain insight from all these feelings and ideas. This process produces a tremendous volume of unstructured data, however, poses a significant risk to the information-extraction procedure and makes decision-making very challenging. This is because excessive data accumulation and improper presentation can lead to the loss of valuable information. The study of detection and emotions in images was advanced by this thesis and it does this by bringing out the feelings and viewpoints buried in a vast amount of image data. To categories the emotions present in photographs, such as people's comments about goods and businesses, personal comment threads, and general messages, a system has been established. This thesis starts by explaining a novel deep neural network-based sentiment analysis technique, which analyses the picture and detect either sentiments are positive or negative. Two models, VGG16 and VGG19, with essentially the same architecture but different parameters, were implemented and trained on two categories (positive and negative). The outcome is quantified in terms of accuracy. VGG16's accuracy is 86.05 percent, while VGG19's accuracy is 86.20 percent. These two models' results demonstrated that VGG19 performs better than VGG16. Researchers in the field of artificial intelligence may use this model to address practical problems like societal and commercial ones. On social media platforms, people use videos and pictures to express their opinions about goods, services, and current affairs, researchers can use this model to detect emotions from such data.
Keywords: Photographs; Social Media; Data
- Ain Q T., et al. “Sentiment analysis using deep learning techniques: a review”. International Journal of Advanced Computer Science and Applications 6 (2017): 424.
- Alex V., et al. “Automatic segmentation and overall survival prediction in gliomas using fully convolutional neural network and texture analysis”. In International MICCAI Brainlesion Workshop (2017): 216-225.
- Acharya T and Ray A K. “Image processing: principles and applications”. John Wiley and Sons (2005).
- Akhtar M S., et al. “Multi-task learning for multi-modal emotion recognition and sentiment analysis”. arXiv preprint (2019): arXiv:1905.05812.
- Ahmad K., et al. “Deep Models for Visual Sentiment Analysis of Disaster-related Multimedia Content”. arXiv preprint arXiv:2112.12060 (2021).
- Albawi S., et al. “Understanding of a convolutional neural network”. In 2017 international conference on engineering and technology (ICET) (2017): 1-6.
- Agarap AF. “Deep learning using rectified linear units (relu)”. arXiv preprint arXiv:1803.08375 (2018).
- Baid P., et al. “Sentiment analysis of movie reviews using machine learning techniques”. International Journal of Computer Applications7 (2017): 45-49.
- Chaovalit P and Zhou L. “Movie review mining: A comparison between supervised and unsupervised classification approaches”. In Proceedings of the 38th annual Hawaii international conference on system sciences (2005): 112c-112c.
- Chatfield K., et al. “Return of the devil in the details: Delving deep into convolutional nets”. arXiv preprint arXiv:1405.3531 (2014).
- Chen P., et al. “Recurrent attention network on memory for aspect sentiment analysis”. In Proceedings of the 2017 conference on empirical methods in natural language processing (2017): 452-461.
- Dy JG and Brodley CE. “Feature selection for unsupervised learning”. Journal of Machine Learning Research 5 (2004): 845-889.
- Deng L and Yu D. “Deep learning: methods and applications”. Foundations and trends® in signal processing 7.3–4 (2014): 197-387.
- Fan ZP., et al. “Product sales forecasting using online reviews and historical sales data: A method combining the Bass model and sentiment analysis”. Journal of Business Research 74 (2017): 90-100.
- Haji SH and Abdulazeez AM. “Comparison of optimization techniques based on gradient descent algorithm: A review”. PalArch's Journal of Archaeology of Egypt/Egyptology4 (2021): 2715-2743.
- Heaton J. “AIFH, volume 3: deep learning and neural networks”. Journal of Chemical Information and Modeling 3 (2015).
- Jeong S. “Investigating Noise Robustness of Convolutional Neural Networks for Image Classification Using Gabor Filters” (Doctoral dissertation, Vanderbilt University) (2020).
- Mittal N., et al. “Image sentiment analysis using deep learning”. In 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI) (20187): 684-687.
- Masters D and Luschi C. “Revisiting small batch training for deep neural networks”. arXiv preprint arXiv:1804.07612 (2018).
- Ombabi A H., et al. “Deep learning CNN–LSTM framework for Arabic sentiment analysis using textual information shared in social networks”. Social Network Analysis and Mining1 (2020): 1-13.
- Ortis A., et al. “Visual sentiment analysis based on on objective text description of images”. In 2018 international conference on content-based multimedia indexing (CBMI) (2018): 1-6.
- Ortis A., et al. “Survey on visual sentiment analysis”. IET Image Processing8 (2020): 1440-1456.
- Petrou M M and Petrou C. “Image processing: the fundamentals”. John Wiley and Sons (2010).
- Recht B., et al. “Do imagenet classifiers generalize to imagenet?”. In International Conference on Machine Learning (2019): 5389-5400.
- Ramachandran P., et al. “Searching for activation functions”. arXiv preprint arXiv:1710.05941 (2017).
- Sadr H., et al. “A Novel Deep Learning Method for Textual Sentiment Analysis”. arXiv preprint arXiv:2102.11651 (2021).
- Shorten C and Khoshgoftaar TM. “A survey on image data augmentation for deep learning”. Journal of Big Data1 (2019): 1-48.
- Simonyan K and Zisserman A. “Very deep convolutional networks for large-scale image recognition”. arXiv preprint arXiv:1409.1556 (2014).
- Sampson T R., et al. “A gut bacterial amyloid promotes α-synuclein aggregation and motor impairment in mice”. Elife 9 (2020): e53111.
- Su T., et al. “A BIM and machine learning integration framework for automated property valuation”. Journal of Building Engineering 44 (2021): 102636.
- Yang Y., et al. “How do your friends on social media disclose your emotions?”. In Proceedings of the AAAI Conference on Artificial Intelligence 28.1 (2014).
- Yadav A., et al. “A deep learning architecture of RA-DLNet for visual sentiment analysis”. Multimedia Systems4 (2020): 431-451.
- Yadav V. “How neural networks learn nonlinear functions and classify linearly non-separable data” (2017).
- You Q., et al. “Robust image sentiment analysis using progressively trained and domain transferred deep networks”. In Twenty-ninth AAAI conference on artificial intelligence (2015).