An Efficient and Accurate GPU-based Deep Learning Model for Multimedia Recommendation
Article No.: 40, Pages 1 - 18
Abstract
This article proposes the use of deep learning in human-computer interaction and presents a new explainable hybrid framework for recommending relevant hashtags on a set of orpheline tweets, which are tweets with hashtags. The approach starts by determining the set of batches used in the convolution neural network based on frequent pattern mining solutions. The convolutional neural network is then applied to the set of batches of tweets to learn the hashtags of the tweets. An optimization strategy has been proposed to accurately perform the learning process by reducing the number of frequent patterns. Moreover, eXplainable AI is introduced for hashtag recommendations by analyzing the user preferences and understanding the different weights of the deep learning model used in the learning process. This is performed by learning the hyper-parameters of the deep architecture using the genetic algorithm. GPU computing is also investigated to achieve high speed and enable the execution of the overall framework in real time. Extensive experimental analysis has been performed to show that our methodology is useful on different collections of tweets. The experimental results clearly show the efficiency of our proposed approach compared to baseline approaches in terms of both runtime and accuracy. Thus, the proposed solution achieves an accuracy of 90% when analyzing complex Wikipedia data while the other algorithms did not achieve 85% when processing the same amount of data.
References
[1]
Rakesh Agrawal, Tomasz Imieliński, and Arun Swami. 1993. Mining association rules between sets of items in large databases. In ACM SIGMOD Record, Vol. 22. 207–216.
[2]
Kashif Ahmad, Mohamed Lamine Mekhalfi, Nicola Conci, Farid Melgani, and Francesco De Natale. 2018. Ensemble of deep models for event recognition. ACM Trans. Multimedia Comput. Commun. Appl. 14, 2 (2018), 1–20.
[3]
Asma Belhadi, Youcef Djenouri, Jerry Chun-Wei Lin, and Alberto Cano. 2020. A data-driven approach for Twitter hashtag recommendation. IEEE Access 8 (2020), 79182–79191.
[4]
Asma Belhadi, Youcef Djenouri, Jerry Chun-Wei Lin, Chongsheng Zhang, and Alberto Cano. 2020. Exploring pattern mining algorithms for hashtag retrieval problem. IEEE Access 8 (2020), 10569–10583.
[5]
Asma Belhadi, Youcef Djenouri, Gautam Srivastava, and Jerry Chun-Wei Lin. 2021. SS-ITS: Secure scalable intelligent transportation systems. The Journal of Supercomputing 77, 7 (2021), 7253–7269.
[6]
Sergey Brin, Rajeev Motwani, Jeffrey D. Ullman, and Shalom Tsur. 1997. Dynamic itemset counting and implication rules for market basket data. In Proceedings of the ACM SIGMOD International Conference on Management of Data. 255–264.
[7]
Da Cao, Lianhai Miao, Huigui Rong, Zheng Qin, and Liqiang Nie. 2020. Hashtag our stories: Hashtag recommendation for micro-videos via harnessing multiple modalities. Knowl.-Based Syst. (2020), 106114.
[8]
Gromit Yeuk-Yin Chan, Panpan Xu, Zeng Dai, and Liu Ren. 2018. ViBr: Visualizing bipartite relations at scale with the minimum description length principle. IEEE Trans. Visual. Comput. Graph. 25, 1 (2018), 321–330.
[9]
Wen-Huang Cheng, Jiaying Liu, Nicu Sebe, Junsong Yuan, and Hong-Han Shuai. 2021. Introduction to the special issue on explainable AI on multimedia computing. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 17, 3 (2021), 1–2.
[10]
Youcef Djenouri and Marco Comuzzi. 2017. Combining a priori heuristic and bio-inspired algorithms for solving the frequent itemsets mining problem. Info. Sci. 420 (2017), 1–15.
[11]
Youcef Djenouri, Marco Comuzzi, and Djamel Djenouri. 2017. SS-FIM: Single scan for frequent itemsets mining in transactional databases. In Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining. 644–654.
[12]
Youcef Djenouri, Djamel Djenouri, and Jerry Chun-Wei Lin. 2021. Trajectory outlier detection: New problems and solutions for smart cities. ACM Trans. Knowl. Discov. Data 15, 2 (2021), 1–28.
[13]
Guanyao Du, Jianying Sun, Xinglong Huang, and Jianjun Yu. 2017. Mining user interests for personalized tweet recommendation on map-reduce framework. In Proceedings of the International Conference on Enterprise Information Systems. 201–208.
[14]
Krzysztof Fiok, Waldemar Karwowski, Edgar Gutierrez, and Maciej Wilamowski. 2021. Analysis of sentiment in tweets addressed to a single domain-specific Twitter account: Comparison of model performance and explainability of predictions. Expert Syst. Appl. (2021), 115771.
[15]
Fréderic Godin, Viktor Slavkovikj, Wesley De Neve, Benjamin Schrauwen, and Rik Van de Walle. 2013. Using topic models for Twitter hashtag recommendation. In Proceedings of the International Conference on World Wide Web. 593–596.
[16]
Yeyun Gong, Qi Zhang, and Xuanjing Huang. 2018. Hashtag recommendation for multimodal microblog posts. Neurocomputing 272 (2018), 170–177.
[17]
Karam Gouda and Mohammed Javeed Zaki. 2001. Efficiently mining maximal frequent itemsets. In Proceedings of the IEEE International Conference on Data Mining. 163–170.
[18]
Fatih Gurcan, Nergiz Ercil Cagiltay, and Kursat Cagiltay. 2021. Mapping human–computer interaction research themes and trends from its existence to today: A topic modeling-based review of past 60 years. Int. J. Hum.-Comput. Interact. 37, 3 (2021), 267–280.
[19]
Seyedmohsen Hosseini, Sifat Kalam, Kash Barker, and Jose E. Ramirez-Marquez. 2020. Scheduling multi-component maintenance with a greedy heuristic local search algorithm. Soft Comput. 24, 1 (2020), 351–366.
[20]
Maksims Ivanovs, Roberts Kadikis, and Kaspars Ozols. 2021. Perturbation-based methods for explaining deep neural networks: A survey. Pattern Recogn. Lett. (2021).
[21]
Fei-Fei Kou, Jun-Ping Du, Cong-Xian Yang, Yan-Song Shi, Wan-Qiu Cui, Mei-Yu Liang, and Yue Geng. 2018. Hashtag recommendation based on multi-features of microblogs. J. Comput. Sci. Technol. 33, 4 (2018), 711–726.
[22]
Nagendra Kumar, Eshwanth Baskaran, Anand Konjengbam, and Manish Singh. 2020. Hashtag recommendation for short social media texts using word-embeddings and external knowledge. Knowl. Info. Syst. (2020), 1–24.
[23]
Kai Lei, Qiuai Fu, Min Yang, and Yuzhi Liang. 2020. Tag recommendation by text classification with attention-based capsule network. Neurocomputing 391 (2020), 65–73.
[24]
Mengmeng Li, Tian Gan, Meng Liu, Zhiyong Cheng, Jianhua Yin, and Liqiang Nie. 2019. Long-tail hashtag recommendation for micro-videos with graph convolutional network. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 509–518.
[25]
Yang Li, Jing Jiang, Ting Liu, Minghui Qiu, and Xiaofei Sun. 2017. Personalized microtopic recommendation on microblogs. ACM Trans. Intell. Syst. Technol. 8, 6 (2017), 77.
[26]
Yun Li, Jie Xu, Yun-Hao Yuan, and Ling Chen. 2017. A new closed frequent itemset mining algorithm based on GPU and improved vertical structure. Concurr. Comput.: Pract. Exper. 29, 6 (2017), e3904.
[27]
Jerry Chun-Wei Lin, Yuanfa Li, Philippe Fournier-Viger, Youcef Djenouri, and Leon Shyue-Liang Wang. 2019. Mining high-utility sequential patterns from big datasets. In Proceedings of the IEEE International Conference on Big Data. 2674–2680.
[28]
Jerry Chun-Wei Lin, Yuyu Zhang, Binbin Zhang, Philippe Fournier-Viger, and Youcef Djenouri. 2019. Hiding sensitive itemsets with multiple objective optimization. Soft Comput. 23, 23 (2019), 12779–12797.
[29]
Yu-Sheng Lin, Zhe-Yu Liu, Yu-An Chen, Yu-Siang Wang, Ya-Liang Chang, and Winston H. Hsu. 2021. xCos: An explainable cosine metric for face verification task. ACM Trans. Multimedia Comput. Commun. Appl. 17, 3s (2021), 1–16.
[30]
Hai Liu, Hanwen Nie, Zhaoli Zhang, and You-Fu Li. 2021. Anisotropic angle distribution learning for head pose estimation and attention understanding in human-computer interaction. Neurocomputing 433 (2021), 310–322.
[31]
Jie Liu, Zhicheng He, and Yalou Huang. 2018. Hashtag2Vec: Learning hashtag representation with relational hierarchical embedding model. In Proceedings of the International Joint Conference on Artificial Intelligence. 3456–3462.
[32]
Yanni Liu, Dongsheng Liu, and Yuwei Chen. 2020. Research on sentiment tendency and evolution of public opinions in social networks of smart city. Complexity 2020 (2020).
[33]
Renfeng Ma, Xipeng Qiu, Qi Zhang, Xiangkun Hu, Yu-Gang Jiang, and Xuanjing Huang. 2019. Co-attention memory network for multimodal microblog’s hashtag recommendation. IEEE Trans. Knowl. Data Eng. 33, 2 (2019), 388–400.
[34]
Raheleh Makki, Eder Carvalho, Axel J. Soto, Stephen Brooks, Maria Cristina Ferreira De Oliveira, Evangelos Milios, and Rosane Minghim. 2018. ATR-Vis: Visual and interactive information retrieval for parliamentary discussions in Twitter. ACM Trans. Knowl. Discov. Data 12, 1 (2018), 3.
[35]
Kaoru Ota, Minh Son Dao, Vasileios Mezaris, and Francesco G. B. De Natale. 2017. Deep learning for mobile multimedia: A survey. ACM Trans. Multimedia Comput. Commun. Appl. 13, 3s (2017), 1–22.
[36]
Yanou Ramon, Tom Vermeire, David Martens, Theodoros Evgeniou, and Olivier Toubia. 2021. How should artificial intelligence explain itself? understanding preferences for explanations generated by XAI algorithms. SSRN Electr. J. (2021).
[37]
Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. 2011. ORB: An efficient alternative to SIFT or SURF. In 2011 International Conference on Computer Vision, IEEE, (2011), 2564–2571.
[38]
Surendra Sedhai and Aixin Sun. 2014. Hashtag recommendation for hyperlinked tweets. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. 831–834.
[39]
Bichen Shi, Georgiana Ifrim, and Neil Hurley. 2016. Learning-to-rank for real-time high-precision hashtag recommendation for streaming news. In Proceedings of the International Conference on World Wide Web. 1191–1202.
[40]
Bichen Shi, Gevorg Poghosyan, Georgiana Ifrim, and Neil Hurley. 2018. Hashtagger+: Efficient high-coverage social tagging of streaming news. IEEE Trans. Knowl. Data Eng. 30, 1 (2018), 43–58.
[41]
Mohammad Shorfuzzaman, M. Shamim Hossain, and Abdulmotaleb El Saddik. 2021. An explainable deep learning ensemble model for robust diagnosis of diabetic retinopathy grading. ACM Trans. Multimedia Comput. Commun. Appl. 17, 3s (2021), 1–24.
[42]
Xiaoyue Tang, Cong Zhang, Weiyi Meng, and Kai Wang. 2020. Joint user mention behavior modeling for mentionee recommendation. Appl. Intell. (2020), 1–16.
[43]
Ke Wang, Liu Tang, Jiawei Han, and Junqiang Liu. 2002. Top down FP-growth for association rule mining. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer, Berlin and Heidelberg, 334–340.
[44]
Yinwei Wei, Zhiyong Cheng, Xuzheng Yu, Zhou Zhao, Lei Zhu, and Liqiang Nie. 2019. Personalized hashtag recommendation for micro-videos. In Proceedings of the ACM International Conference on Multimedia. 1446–1454.
[45]
Yong Wu, Shengqu Xi, Yuan Yao, Feng Xu, Hanghang Tong, and Jian Lu. 2018. Guiding supervised topic modeling for content-based tag recommendation. Neurocomputing 314 (2018), 479–489.
[46]
Qi Yang, Gaosheng Wu, Yuhua Li, Ruixuan Li, Xiwu Gu, Huicai Deng, and Junzhuang Wu. 2020. AMNN: Attention-based multimodal neural network model for hashtag recommendation. IEEE Trans. Comput. Soc. Syst. (2020).
[47]
Yesuel Kim and Youngchul Kim. 2022. Explainable heat-related mortality with random forest and SHapley Additive exPlanations (SHAP) models. Sustain. Cities Soc. 79 (2022), 103677.
[48]
Binbin Zhang, Jerry Chun-Wei Lin, Yinan Shao, Philippe Fournier-Viger, and Youcef Djenouri. 2018. Maintenance of discovered high average-utility itemsets in dynamic databases. Appl. Sci. 8, 5 (2018), 769.
[49]
Siyuan Zhang and Hong Cheng. 2018. Exploiting context graph attention for POI recommendation in location-based social networks. In Proceedings of the International Conference on Database Systems for Advanced Applications. 83–99.
[50]
Feng Zhao, Yajun Zhu, Hai Jin, and Laurence T. Yang. 2016. A personalized hashtag recommendation approach using LDA-based topic model in microblog environment. Future Gen. Comput. Syst. 65 (2016), 196–206.
Index Terms
- An Efficient and Accurate GPU-based Deep Learning Model for Multimedia Recommendation
Recommendations
Deep learning based hashtag recommendation system for multimedia data
AbstractThis work aims to provide a novel hybrid architecture to suggest appropriate hashtags to a collection of orpheline tweets. The methodology starts with defining the collection of batches used in the convolutional neural network. This ...
Towards a deep learning model for hybrid recommendation
WI '17: Proceedings of the International Conference on Web IntelligenceThe deep learning wave is propagating through many research areas and communities. In the last years it quickly propagated to Recommendation Systems, a research area which aims to recommend items to users. Indeed, many deep learning models and ...
Review of Deep Learning-Based Personalized Learning Recommendation
IC4E '20: Proceedings of the 2020 11th International Conference on E-Education, E-Business, E-Management, and E-LearningOnline learning has become a significant way for learners to acquire knowledge, which enables anybody to learn anywhere and anytime. However, how to choose appropriate content for learning is an interesting issue, especially when one faces massive ...
Comments
Information & Contributors
Information
Published In
February 2024
548 pages
ISSN:1551-6857
EISSN:1551-6865
DOI:10.1145/3613570
- Editor:
- Abdulmotaleb El Saddik
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 25 September 2023
Online AM: 12 March 2022
Accepted: 02 March 2022
Revised: 27 January 2022
Received: 14 October 2021
Published in TOMM Volume 20, Issue 2
Check for updates
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 343Total Downloads
- Downloads (Last 12 months)155
- Downloads (Last 6 weeks)6
Reflects downloads up to 27 Jul 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in