Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms
Popularity prediction using social media is an important task because of its wide range of real-world applications such as advertisements, recommendation systems, and trend analysis. However, this task is challenging because social media is affected by multiple factors that cannot be easily modeled...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9656132/ |
| _version_ | 1798025554434195456 |
|---|---|
| author | Hung-Hsiang Lin Jiun-Da Lin Jose Jaena Mari Ople Jun-Cheng Chen Kai-Lung Hua |
| author_facet | Hung-Hsiang Lin Jiun-Da Lin Jose Jaena Mari Ople Jun-Cheng Chen Kai-Lung Hua |
| author_sort | Hung-Hsiang Lin |
| collection | DOAJ |
| description | Popularity prediction using social media is an important task because of its wide range of real-world applications such as advertisements, recommendation systems, and trend analysis. However, this task is challenging because social media is affected by multiple factors that cannot be easily modeled (e.g. quality of content, relevance to viewers, real-life events). Usually, other methods adopt the greedy approach to include as many modalities and factors as possible into their model but treat these features equally. To solve this phenomenon, our proposed method leverages the self-attention mechanism to effectively and automatically fuse different features to achieve better performance for the popularity prediction of a post, where the features used in our model can be mainly categorized into two modalities, semantic (text) and numeric features. With extensive experiments and ablation studies on the training and testing data of the challenging ACM Multimedia SMPD 2020 Challenge dataset, the evaluation results demonstrate the effectiveness of the proposed approach as compared with other methods. |
| first_indexed | 2024-04-11T18:22:04Z |
| format | Article |
| id | doaj.art-59486aa12923413a9db766f03cb46f1d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T18:22:04Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-59486aa12923413a9db766f03cb46f1d2022-12-22T04:09:45ZengIEEEIEEE Access2169-35362022-01-01104448445510.1109/ACCESS.2021.31365529656132Social Media Popularity Prediction Based on Multi-Modal Self-Attention MechanismsHung-Hsiang Lin0https://orcid.org/0000-0002-5272-7127Jiun-Da Lin1Jose Jaena Mari Ople2Jun-Cheng Chen3https://orcid.org/0000-0002-0209-8932Kai-Lung Hua4https://orcid.org/0000-0002-7735-243XDepartment of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, TaiwanDepartment of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, TaiwanDepartment of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, TaiwanResearch Center for Information Technology Innovation, Academia Sinica, Taipei, TaiwanDepartment of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, TaiwanPopularity prediction using social media is an important task because of its wide range of real-world applications such as advertisements, recommendation systems, and trend analysis. However, this task is challenging because social media is affected by multiple factors that cannot be easily modeled (e.g. quality of content, relevance to viewers, real-life events). Usually, other methods adopt the greedy approach to include as many modalities and factors as possible into their model but treat these features equally. To solve this phenomenon, our proposed method leverages the self-attention mechanism to effectively and automatically fuse different features to achieve better performance for the popularity prediction of a post, where the features used in our model can be mainly categorized into two modalities, semantic (text) and numeric features. With extensive experiments and ablation studies on the training and testing data of the challenging ACM Multimedia SMPD 2020 Challenge dataset, the evaluation results demonstrate the effectiveness of the proposed approach as compared with other methods.https://ieeexplore.ieee.org/document/9656132/Social media popularity predictionensemble learningmulti-modalityself-attentionimage caption |
| spellingShingle | Hung-Hsiang Lin Jiun-Da Lin Jose Jaena Mari Ople Jun-Cheng Chen Kai-Lung Hua Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms IEEE Access Social media popularity prediction ensemble learning multi-modality self-attention image caption |
| title | Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms |
| title_full | Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms |
| title_fullStr | Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms |
| title_full_unstemmed | Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms |
| title_short | Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms |
| title_sort | social media popularity prediction based on multi modal self attention mechanisms |
| topic | Social media popularity prediction ensemble learning multi-modality self-attention image caption |
| url | https://ieeexplore.ieee.org/document/9656132/ |
| work_keys_str_mv | AT hunghsianglin socialmediapopularitypredictionbasedonmultimodalselfattentionmechanisms AT jiundalin socialmediapopularitypredictionbasedonmultimodalselfattentionmechanisms AT josejaenamariople socialmediapopularitypredictionbasedonmultimodalselfattentionmechanisms AT junchengchen socialmediapopularitypredictionbasedonmultimodalselfattentionmechanisms AT kailunghua socialmediapopularitypredictionbasedonmultimodalselfattentionmechanisms |