Deep-profiling: a deep neural network model for scholarly Web user profiling

Scholarly big data refer to the rapidly growing scholarly source of information, including a large number of authors, papers, and massive scale scholarly networks. Extracting the profile attributes for Web users is an important step in Web user analysis. For Web scholarly users, profile attributes extraction should integrate multi-source and heterogeneous information resources. However, the traditional extraction models have two main drawbacks: (1) The traditional models require manual feature selection based on specific domain knowledge; (2) The traditional models cannot adapt to the diversities of Scholarly Web pages and cannot discover the relationships between different target entities which are far apart in different domains. To address these issues, we propose a profile attributes extraction model, PAE-NN, based on a Bi-LSTM-CRF neural network. This model can automatically extract the characteristics and contextual representations of each extracting entity through a Recurrent Neural Network with end-to-end training. It takes advantage of the long-memory sequence characteristics of LSTM network to effectively discover the long-term dependencies on extracting entities. Our experimental results on published datasets from the SMPCUP2017 Open Academic Competition and Aminer demonstrate that the proposed PAE-NN model outperforms existing models in terms of extraction precision, recall, and F1-score with large-scale training data.

[1]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[2]  Xin Chang,et al.  Multi-Information Spatial–Temporal LSTM Fusion Continuous Sign Language Neural Machine Translation , 2020, IEEE Access.

[3]  Eduard H. Hovy,et al.  Weakly Supervised User Profile Extraction from Twitter , 2014, ACL.

[4]  Jie Tang,et al.  AMiner: Toward Understanding Big Scholar Data , 2016, WSDM.

[5]  Wenyi Huang,et al.  Towards building a scholarly big data platform: Challenges, lessons and opportunities , 2014, IEEE/ACM Joint Conference on Digital Libraries.

[6]  Vimal Kumar,et al.  Combating Deepfakes: Multi-LSTM and Blockchain as Proof of Authenticity for Digital Media , 2020, 2020 IEEE / ITU International Conference on Artificial Intelligence for Good (AI4G).

[7]  Hong Yang,et al.  Profiling Web users using big data , 2018, Social Network Analysis and Mining.

[8]  Rajiv Kapoor,et al.  English-Hindi Neural Machine Translation-LSTM Seq2Seq and ConvS2S , 2020, 2020 International Conference on Communication and Signal Processing (ICCSP).

[9]  Yi Yang,et al.  A User Profile Modeling Method Based on Word2Vec , 2017, 2017 IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C).

[10]  B. Janet,et al.  Sentiment Analysis of US Airlines Tweets Using LSTM/RNN , 2019, 2019 IEEE 9th International Conference on Advanced Computing (IACC).

[11]  Abdullah G. Alharbi,et al.  Deep Learning-Based Stock Price Prediction Using LSTM and Bi-Directional LSTM Model , 2020, 2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES).

[12]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[13]  Madian Khabsa,et al.  Digital commons , 2020, Internet Policy Rev..

[14]  Li Zhang,et al.  Mapping the Scholarly Literature Found in Scopus on “Research Data Management”: A Bibliometric and Data Visualization Approach , 2019, Journal of Librarianship and Scholarly Communication.

[15]  Xinbing Wang,et al.  AceMap: A Novel Approach towards Displaying Relationship among Academic Literatures , 2016, WWW.

[16]  Maho Wielfrid Morie,et al.  Information Extraction Model to Improve Learning Game Metadata Indexing , 2020, Ingénierie des Systèmes d Inf..

[17]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[18]  Aleksander Colovic,et al.  End-to-End Training of Hybrid CNN-CRF Models for Semantic Segmentation using Structured Learning , 2017 .

[19]  Yifei Lu,et al.  LSTM-BA: DDoS Detection Approach Combining LSTM and Bayes , 2019, 2019 Seventh International Conference on Advanced Cloud and Big Data (CBD).

[20]  Feng Yuan,et al.  Multi-task learning based on question–answering style reviews for aspect category classification and aspect term extraction on GPU clusters , 2020, Cluster Computing.

[21]  Tat-Seng Chua,et al.  Harvesting Multiple Sources for User Profile Learning: a Big Data Study , 2015, ICMR.

[22]  Jie Tang,et al.  A Combination Approach to Web User Profiling , 2010, TKDD.

[23]  Krys J. Kochut,et al.  A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques , 2017, ArXiv.

[24]  Philip S. Yu,et al.  COSNET: Connecting Heterogeneous Social Networks with Local and Global Consistency , 2015, KDD.

[25]  Xing Huang,et al.  A LSTM-based bidirectional translation model for optimizing rare words and terminologies , 2018, 2018 International Conference on Artificial Intelligence and Big Data (ICAIBD).

[26]  Feng Xia,et al.  Big Scholarly Data: A Survey , 2017, IEEE Transactions on Big Data.

[27]  Thomas Pock,et al.  End-to-End Training of Hybrid CNN-CRF Models for Stereo , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Md. Rafiuzzaman Bhuiyan,et al.  Sentiment Analysis of Restaurant Reviews using Combined CNN-LSTM , 2020, 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT).

[29]  Stavros Shiaeles,et al.  Localising social network users and profiling their movement , 2019, Comput. Secur..

[30]  Omar Alonso,et al.  Quantitative Information Extraction From Social Data , 2018, SIGIR.

[31]  Matan Levi,et al.  User Profiling Using Sequential Mining Over Web Elements , 2019, 2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[32]  Qinghua Lu,et al.  Combining Attributes and Links: Finding Homepage for Entity Searching , 2015, 2015 International Conference on Computational Intelligence and Communication Networks (CICN).

[33]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[34]  Guillaume Lample,et al.  Neural Architectures for Named Entity Recognition , 2016, NAACL.

[35]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[36]  Carsten Rother,et al.  Joint Training of Generic CNN-CRF Models with Stochastic Optimization , 2016, ACCV.

[37]  L. Maria Michael Visuwasam,et al.  NMA: integrating big data into a novel mobile application using knowledge extraction for big data analytics , 2018, Cluster Computing.

[38]  Xiaohong Liu,et al.  Research on Chinese Named Entity Recognition Based on Neural Network , 2018, 2018 IEEE 4th International Conference on Computer and Communications (ICCC).

[39]  Xiang Ren,et al.  Empower Sequence Labeling with Task-Aware Neural Language Model , 2017, AAAI.