ABSTRACT
In the recent years, there are huge data extracted from social networks in both static and real-time analysis, such as Facebook, Twitter, LinkedIn, and Instagram. Recently, most researchers have investigated in classifying textual contents without user interests/behaviors from huge data of social networks. This paper has presented a novel approach using a Convolution Neural Network with its new contribution of user perceptions from the social network data to classifying the user interests. Experimental results show that the proposed model performs better than the conventional algorithms in terms of classifying user interests. Additionally, the proposed model enhances a quality of classification for user interests tracking real-time in social networks.
- Can, U. and Alatas, B. 2019. A new direction in social network analysis: Online social network analysis problems and applications. Physica A: Statistical Mechanics and its Applications. 535, (2019), 122372. DOI:https://doi.org/10.1016/j.physa.2019.122372.Google ScholarCross Ref
- Nandi, G. and Das, A. 2014. Online Social Network Mining: Current Trends and Research Issues. International Journal of Research in Engineering and Technology. 03, 04 (2014), 346--350. DOI:https://doi.org/10.15623/ijret.2014.0304062.Google Scholar
- Jin, L. et al. 2013. Understanding User Behavior in Online Social Networks: A Survey CONNECTIVITY AND INTERACTION MOTIVATION AND CHALLENGES. IEEE Communications Magazine. September (2013), 144--150.Google Scholar
- Statista, Leading countries based on number of Facebook users as of April 2019 (in millions), URL: https://www.statista.com/statistics/268136/top-15-countries-based-on-numGoogle Scholar
- Sengupta, S. et al. 2019. A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends. XX, March (2019).Google Scholar
- Siswanto, E. et al. 2015. Prediction of interest for dynamic profile of Twitter user. Proceedings - 2014 International Conference on Advanced Informatics: Concept, Theory and Application, ICAICTA 2014. (2015), 266--271. DOI:https://doi.org/10.1109/ICAICTA.2014.7005952.Google ScholarCross Ref
- Raghuram, M.A. et al. 2018. Intelligent Systems Technologies and Applications. 683, (2018), 399--400. DOI:https://doi.org/10.1007/978-3-319-68385-0.Google Scholar
- Jiliang Tang, S.A. and and Liu, H. 2014. Feature Selection for Classification: A Review. Data Classification: Algorithms and Applications. (2014), 571--605. DOI:https://doi.org/10.1201/b17320.Google Scholar
- Kim, H. and Jeong, Y.S. 2019. Sentiment classification using Convolutional Neural Networks. Applied Sciences (Switzerland). 9, 11 (2019), 1--14. DOI:https://doi.org/10.3390/app9112347.Google Scholar
- Van Pham H., Son L.H., Tuan L.M. (2020) A Proposal of Expert System Using Deep Learning Neural Networks and Fuzzy Rules for Diagnosing Heart Disease. Frontiers in Intelligent Computing: Theory and Applications. Advances in Intelligent Systems and Computing, vol 1013. Springer, Singapore, pp. 189--198.Google Scholar
- Hai V. Pham, Fujita Y. and Kamei K., Hybrid Artificial Neural Networks for TBM Utilization and Performance Prediction in Complex Underground Conditions, Proceedings of the 2011 IEEE International Symposium on System Integration, IEEE, pp.1149--1154, December 2011, Kyoto, Japan..Google Scholar
- Philip Moore, Hai V. Pham, Predicting Intelligence Using Hybrid Artificial Neural Networks in Context-Aware Tunneling Systems under Risk and Uncertain Geological Environment, Second International Workshop on Intelligent Context-Aware Systems (ICAS 2012), pp.989--994, ItaliaGoogle Scholar
- Alharbi, A.S.M. and de Doncker, E. 2019. Twitter sentiment analysis with a deep neural network: An enhanced approach using user behavioral information. Cognitive Systems Research. 54, (2019), 50--61. DOI:https://doi.org/10.1016/j.cogsys.2018.10.001.Google Scholar
- Davidov, D. et al. 2010. Enhanced Sentiment Learning Using Twitter Hashtags and Smileys. August (2010), 241--249.Google Scholar
- Jamali, M. and Abolhassani, H. 2007. Different aspects of social network analysis. Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06. (2007), 66--72. DOI:https://doi.org/10.1109/WI.2006.61.Google ScholarDigital Library
- Irfan Ahmad, 2019. The Most Popular Social Media Platforms of 2019. Digital information world. URL: https://www.digitalinformationworld.com/2019/01/most-popular-global-social-networks-apps-infographic.html#postimagesGoogle Scholar
- Singh, A. et al. 2019. An Analysis of Demographic and Behavior Trends Using Social Media: Facebook, Twitter, and Instagram. Elsevier Inc.Google Scholar
- David Kaplan, 2017. Amazon's Neptune Database Will Expand The Knowledge Graph. Geo marketing From Yext. URL: https://geomarketing.com/amazons-neptune-database-will-expand-the-knowledge-graph-heres-howGoogle Scholar
- Pang, B. et al. 2011. Sentiment Classification using Machine Learning Techniques. Proceedings - Symposium on Logic in Computer Science. July (2011), 97--106. DOI:https://doi.org/10.1109/LICS.2011.23.Google ScholarDigital Library
- Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron (2016). "6.2.2.3 Softmax Units for Multinoulli Output Distributions". Deep Learning. MIT Press. pp. 180--184Google Scholar
- https://github.com/truongdx5/FacebookCrawl/blob/master/DATASET.csvGoogle Scholar
- Nichols, G.J. and Fisher, J.A. 2007. Processes, facies and architecture of fluvial distributary system deposits. Sedimentary Geology. 195, 1--2 (2007), 75--90. DOI:https://doi.org/10.1016/j.sedgeo.2006.07.004.Google ScholarCross Ref
- Goncalves, P. et al. 2013. Comparing and Combining Sentiment Analysis Methods Categories and Subject Descriptors. Proceedings of the first ACM conference on Online social networks. (2013), 27--38. DOI:https://doi.org/10.1145/2512938.2512951.Google ScholarDigital Library
Index Terms
- A Proposal of Deep Learning Model for Classifying User Interests on Social Networks
Recommendations
Deep recurrent convolutional networks for inferring user interests from social media
AbstractOnline social media services, such as Facebook and Twitter, have recently increased in popularity. Although determining the subjects of individual posts is important for extracting users’ interests from social media, this task is nontrivial ...
The Relationship between Online Social Network Ties and User Attributes
The distance between users has an effect on the formation of social network ties, but it is not the only or even the main factor. Knowing all the features that influence such ties is very important for many related domains such as location-based ...
Characterizing the interests of social media users
Recent research has focused on extracting personal interest data from social media. Although many methods have been developed, accurately estimating users' interests is often difficult because messages on social media are short and are not classified ...
Comments