Animated Graphics Interchange Format (GIF) images have become an important part of network information interaction, and are one of the main characteristics of analyzing social media emotions. At present, most of the research on GIF affection recognition fails to make full use of spatial-temporal characteristics of GIF images, which limits the performance of model recognition to a certain extent. A GIF emotion recognition algorithm based on ResNet-ConvGRU is proposed in this paper. First, GIF data is preprocessed, converting its image sequences to static image format for saving. Then, the spatial features of images and the temporal features of static image sequences are extracted with ResNet and ConvGRU networks, respectively. At last, the animated GIFs data features are synthesized and the seven emotional intensities of GIF data are calculated. The GIFGIF dataset is used to verify the experiment. From the experimental results, the proposed animated GIFs emotion recognition model based on ResNet-ConvGRU, compared with the classical emotion recognition algorithms such as VGGNet-ConvGRU, ResNet3D, CNN-LSTM, and C3D, has a stronger feature extraction ability, and sentiment classification performance. This method provides a finer-grained analysis for the study of public opinion trends and a new idea for affection recognition of GIF data in social media.
In order to solve some problems of traditional machine learning algorithms in Mongolian sentiment analysis tasks, such as low accuracy, few sentiment corpus, and poor training effect, a Traditional Mongolian sentiment classification algorithm integrates prior knowledge is proposed. First and foremost, 1.3 million unlabeled Mongolian corpora are pre-trained and preliminarily segmented to obtain basic Mongolian vocabulary information. Secondly, the regularization method is used to segment the corpus. Next, a Mongolian text sentiment dictionary is created, which is used as prior knowledge. At the same time, an attention mechanism is integrated into the model to obtain emotional features in a dynamic form. In the last step, based on the Mongolian sentiment data set, the model is further trained and slightly modified to obtain the final traditional Mongolian sentiment analysis model. From the experimental results, the proposed model, compared with the classical sentiment classification algorithms such as Fasttext, BiLSTM, and CNN, has stronger feature extraction ability, sentiment classification performance, and faster convergence speed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.