Filters








64,115 Hits in 9.1 sec

Predicting User Roles in Social Networks Using Transfer Learning with Feature Transformation

Jun Sun, Jerome Kunegis, Steffen Staab
2016 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)  
We present a transfer learning approach to network role classification based on feature transformations from each network's local feature distribution to a global feature space.  ...  How can we recognise social roles of people, given a completely unlabelled social network?  ...  CONCLUSION In this paper, we proposed a transfer learning-based approach with feature transformation to predict user roles in social networks.  ... 
doi:10.1109/icdmw.2016.0026 dblp:conf/icdm/SunKS16 fatcat:ghpx7ntj2ndkzaw6ijfjyjdfwe

Understanding Social Networks Using Transfer Learning

Jun Sun, Steffen Staab, Jerome Kunegis
2018 Computer  
We compare the performance of TraNet with other approaches and find that our approach can best transfer knowledge on users across platforms in the given tasks.  ...  We show two use cases where TraNet is applied to tasks involving the identification of user trust and roles on different Web platforms.  ...  Applications We now illustrate two concrete applications of TraNet as examples: identifying trusted users in social networks on the Web (in Section 4.2) and identifying users with specific roles (in Section  ... 
doi:10.1109/mc.2018.2701640 fatcat:efuegsdotvhtvg5uq3eksak4ry

Automated PII Extraction from Social Media for Raising Privacy Awareness: A Deep Transfer Learning Approach [article]

Yizhi Liu, Fang Yu Lin, Mohammadreza Ebrahimi, Weifeng Li, Hsinchun Chen
2021 arXiv   pre-print
In this study, we propose the Deep Transfer Learning for PII Extraction (DTL-PIIE) framework to address these two limitations.  ...  While Information Extraction (IE) techniques can be used to extract the PII automatically, Deep Learning (DL)-based IE models alleviate the need for feature engineering and further improve the efficiency  ...  A CRF layer is then used to predict the label of each word in a sentence.  ... 
arXiv:2111.09415v1 fatcat:5carl4zvszebdc2pi7xb6uttkm

Collective Link Prediction Oriented Network Embedding with Hierarchical Graph Attention [article]

Yizhu Jiao, Yun Xiong, Jiawei Zhang, Yangyong Zhu
2019 arXiv   pre-print
To enjoy more social network services, users nowadays are usually involved in multiple online sites at the same time.  ...  In this paper, we target on the collective link prediction problem and aim to predict both the intra-network social links as well as the inter-network anchor links across multiple aligned social networks  ...  ACKNOWLEDGMENTS is work is supported in part by the National Natural Science Foundation of China Projects No.U1636207 and NSF through grant IIS-1763365. is work is also partially supported by the Shanghai  ... 
arXiv:1910.05736v1 fatcat:cvevraqagnbhfosurrv7mfn2zq

Modelling the Latent Semantics of Diffusion Sources in Information Cascade Prediction

Ningbo Huang, Gang Zhou, Mengli Zhang, Meng Zhang, Ze Yu, Thippa Reddy G
2021 Computational Intelligence and Neuroscience  
To learn the latent interaction between users and diffusion sources, we proposed a co-attention-based fusion gate which fuses the diffusion sources' latent semantics with user embedding.  ...  The existing information cascade prediction models are devoted to extract the chronological features from diffusion sequences but treat the diffusion sources as ordinary users.  ...  Acknowledgments is work was supported in part by the Henan Science and Technology Research Project (No. 192102210129).  ... 
doi:10.1155/2021/7880215 pmid:34630553 pmcid:PMC8494548 fatcat:niy7ypw7eraqhpuq5yvanutis4

Spontaneous Facial Behavior Analysis using Deep Transformer Based Framework for Child–Computer Interaction

Abdul Qayyum, Imran Razzak, M. Tanveer, Moona Mazher
2022 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
representations using cross-feature fusion technique to predict users emotions.  ...  In this work, we analyzed the child's spontaneous behavior using multimodal facial expression and voice signal presenting multimodal transformer-based last feature fusion for facial behavior analysis in  ...  Emotions are essential for communication as well as for social interaction and play a crucial role in decision-making hence critical in our daily lives, i.e., how we engage with others and live our lives  ... 
doi:10.1145/3539577 fatcat:qec7mjasevhupkmihllddcxwqe

D2D-LSTM: LSTM-Based Path Prediction of Content Diffusion Tree in Device-to-Device Social Networks

Heng Zhang, Xiaofei Wang, Jiawen Chen, Chenyang Wang, Jianxin Li
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
With the proliferation of mobile device users, the Device-to-Device (D2D) communication has ascended to the spotlight in social network for users to share and exchange enormous data.  ...  To the best of our knowledge, it is the first attempt to use real world large-scale dataset of mobile social network (MSN) to predict propagation path trees in a top-down order.  ...  Second, we conclude the social characteristics of users playing an essential role in D2D transmission path prediction.  ... 
doi:10.1609/aaai.v34i01.5363 fatcat:okawufshdnfotewzfrkssph3yy

A Systematic Review of Machine Learning Algorithms in Cyberbullying Detection: Future Directions and Challenges

Muhammad Arif
2021 Journal of Information Security and Cybercrimes Research  
Social media networks are becoming an essential part of life for most of the world's population.  ...  Detecting cyberbullying using machine learning and natural language processing algorithms is getting the attention of researchers.  ...  Personality prediction from the social media traces can help predict the roles of users in a cyberbullying event.  ... 
doi:10.26735/gbtv9013 fatcat:jttkjrbsqndytlmr4yqoik23j4

Experimental Evaluation of Clickbait Detection Using Machine Learning Models

Iftikhar Ahmad, Mohammed A. Alqarni, Abdulwahab Ali Almazroi, Abdullah Tariq
2020 Intelligent Automation and Soft Computing  
With such an intention, tempting headlines, which are not aligned with the content, are being used to lure users to visit the websites that often post dodgy and unreliable information.  ...  (LSTM), Parallel Convolutional Network (PNN), and Bidirectional Encoder Representations from Transformers (BERT) for automated clickbait detection.  ...  Social networking applications also help people understand various cultures and can play a key role in cross culture understanding.  ... 
doi:10.32604/iasc.2020.013861 fatcat:42gn2rl4dfglpoxmm25qghc2sy

Graph Neural Networks for User Identity Linkage [article]

Wen Zhang, Kai Shu, Huan Liu, Yalin Wang
2019 arXiv   pre-print
With the recent advancements in graph neural networks (GNNs), it provides great potential to advance user identity linkage since users are connected in social graphs, and learning latent factors of users  ...  Each user may create a user identity to represent his or her unique public figure in every social network.  ...  In a social network, a user plays a unique role when interacting with other users.  ... 
arXiv:1903.02174v1 fatcat:pzktq4ld7vbxna3ulzisfy3lge

Link Prediction and Recommendation across Heterogeneous Social Networks

Yuxiao Dong, Jie Tang, Sen Wu, Jilei Tian, Nitesh V. Chawla, Jinghai Rao, Huanhuan Cao
2012 2012 IEEE 12th International Conference on Data Mining  
With the general social patterns, we develop a transfer-based RFG model that combines them with network structure information.  ...  Link prediction and recommendation is a fundamental problem in social network analysis.  ...  [21] presents a unified framework for learning link prediction and edge weight prediction functions in large networks, based on the transformation of a graph's algebraic spectrum.  ... 
doi:10.1109/icdm.2012.140 dblp:conf/icdm/DongTWTCRC12 fatcat:jojr3sa7bzhwrebu2bfi7wntiy

Smart Citizen Sensing: A Proposed Computational System with Visual Sentiment Analysis and Big Data Architecture

Kaoutar Ben, Mohammed Bouhorma, Mohamed Ben
2016 International Journal of Computer Applications  
This work explores deep features of photos shared by users in Twitter via convolutional neural networks and transfer learning to predict sentiments.  ...  This paper presents a novel approach to perform visual sentiment analysis of big visual data shared on social networks (such as Facebook, Twitter, LinkedIn, and Pinterest) using transfer learning.  ...  Our computational system uses convolutional neural networks and transfer learning for visual sentiment prediction.  ... 
doi:10.5120/ijca2016911880 fatcat:sqvunitc2bd5zinhk2aaklqxvq

A Multi-task Multi-kernel Transfer Learning Method for Customer Response Modeling in Social Media

Minghe Sun, Zhen-Yu Chen, Zhi-Ping Fan
2014 Procedia Computer Science  
In this study, a multi-task multi-kernel transfer learning (MT-MKTL) method is proposed to integrate shared, task-specific and transferred features in a framework for customer response modeling in social  ...  With the development of social media, customer response modeling in social media plays important roles in the firms' marketing decisions.  ...  The scenarios s1 and s2 use transfer learning, i.e., use the transferred features of Task B to predict the users' responses to Task A, while the scenario s3 does not use transfer learning, i.e., predicts  ... 
doi:10.1016/j.procs.2014.05.263 fatcat:ytfhc56t35gildgmdnyawk6mum

Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models

Benedek Rozemberczki, Rik Sarkar
2020 Proceedings of the 29th ACM International Conference on Information & Knowledge Management  
We argue that features extracted by this procedure are useful for node level machine learning tasks.  ...  Using the node feature characteristic functions we define parametric models where evaluation points of the functions are learned parameters of supervised classifiers.  ...  ACKNOWLEDGEMENTS Benedek Rozemberczki was supported by the Centre for Doctoral Training in Data Science, funded by EPSRC (grant EP/L016427/1).  ... 
doi:10.1145/3340531.3411866 dblp:conf/cikm/RozemberczkiS20 fatcat:bnn7dpipi5fmnj72442rdto4xy

Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models [article]

Benedek Rozemberczki, Rik Sarkar
2020 arXiv   pre-print
We argue that features extracted by this procedure are useful for node level machine learning tasks.  ...  Using the node feature characteristic functions we define parametric models where evaluation points of the functions are learned parameters of supervised classifiers.  ...  ACKNOWLEDGEMENTS Benedek Rozemberczki was supported by the Centre for Doctoral Training in Data Science, funded by EPSRC (grant EP/L016427/1).  ... 
arXiv:2005.07959v2 fatcat:hoodhsanjfh7bazngmo2ovj6vq
« Previous Showing results 1 — 15 out of 64,115 results