Research Topic Recommendation Based on Latent Dirichlet Allocation

Hongshu Chen; Xuefeng Wang; Yahui Song; Ximeng Wang; Xiang Wang; Miaomiao Yu

doi:10.1109/ISKE47853.2019.9170324

Research Topic Recommendation Based on Latent Dirichlet Allocation

Hongshu Chen, Xuefeng Wang, Yahui Song, Ximeng Wang, Xiang Wang, Miaomiao Yu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Knowledge discovery pushes every discipline, including bibliometrics and innovation management, to reposition itself and stay competitive. With the exponential growth of scientific literature, it has become increasingly difficult for researchers to quickly and effectively identify potential research topics in an interested area to advance their research. This has led to the development of research topic recommendation. In this paper, aiming to explore the potential author-topic relations in depth, we proposed a research topic recommendation methodology based on latent Dirichlet allocation and bipartite network analysis, to predict the inspiring research topics that an author potentially will be interested and working on. A case study on scientific literature in the area of knowledge discovery is then presented to demonstrate the feasibility of the methodology. The result of this research could assist academic researchers in identifying and extending potential research directions.

Original language	English
Title of host publication	Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019
Editors	Li Zou, Lingling Fang, Bo Fu, Panpan Niu
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	637-643
Number of pages	7
ISBN (Electronic)	9781728123486
DOIs	https://doi.org/10.1109/ISKE47853.2019.9170324
Publication status	Published - Nov 2019
Event	14th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019 - Dalian, China Duration: 14 Nov 2019 → 16 Nov 2019

Publication series

Name	Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019

Conference

Conference	14th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019
Country/Territory	China
City	Dalian
Period	14/11/19 → 16/11/19

Keywords

bipartite networks
latent Dirichlet allocation
link prediction
topic modeling

Access to Document

10.1109/ISKE47853.2019.9170324

Cite this

Chen, H., Wang, X., Song, Y., Wang, X., Wang, X., & Yu, M. (2019). Research Topic Recommendation Based on Latent Dirichlet Allocation. In L. Zou, L. Fang, B. Fu, & P. Niu (Eds.), Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019 (pp. 637-643). Article 9170324 (Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISKE47853.2019.9170324

Chen, Hongshu ; Wang, Xuefeng ; Song, Yahui et al. / Research Topic Recommendation Based on Latent Dirichlet Allocation. Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019. editor / Li Zou ; Lingling Fang ; Bo Fu ; Panpan Niu. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 637-643 (Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019).

@inproceedings{20574e924b0d4397a2f0d65b5c721e70,

title = "Research Topic Recommendation Based on Latent Dirichlet Allocation",

abstract = "Knowledge discovery pushes every discipline, including bibliometrics and innovation management, to reposition itself and stay competitive. With the exponential growth of scientific literature, it has become increasingly difficult for researchers to quickly and effectively identify potential research topics in an interested area to advance their research. This has led to the development of research topic recommendation. In this paper, aiming to explore the potential author-topic relations in depth, we proposed a research topic recommendation methodology based on latent Dirichlet allocation and bipartite network analysis, to predict the inspiring research topics that an author potentially will be interested and working on. A case study on scientific literature in the area of knowledge discovery is then presented to demonstrate the feasibility of the methodology. The result of this research could assist academic researchers in identifying and extending potential research directions.",

keywords = "bipartite networks, latent Dirichlet allocation, link prediction, topic modeling",

author = "Hongshu Chen and Xuefeng Wang and Yahui Song and Ximeng Wang and Xiang Wang and Miaomiao Yu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 14th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019 ; Conference date: 14-11-2019 Through 16-11-2019",

year = "2019",

month = nov,

doi = "10.1109/ISKE47853.2019.9170324",

language = "English",

series = "Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "637--643",

editor = "Li Zou and Lingling Fang and Bo Fu and Panpan Niu",

booktitle = "Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019",

address = "United States",

}

Chen, H , Wang, X, Song, Y, Wang, X, Wang, X & Yu, M 2019, Research Topic Recommendation Based on Latent Dirichlet Allocation. in L Zou, L Fang, B Fu & P Niu (eds), Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019., 9170324, Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019, Institute of Electrical and Electronics Engineers Inc., pp. 637-643, 14th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019, Dalian, China, 14/11/19. https://doi.org/10.1109/ISKE47853.2019.9170324

Research Topic Recommendation Based on Latent Dirichlet Allocation. / Chen, Hongshu ; Wang, Xuefeng; Song, Yahui et al.
Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019. ed. / Li Zou; Lingling Fang; Bo Fu; Panpan Niu. Institute of Electrical and Electronics Engineers Inc., 2019. p. 637-643 9170324 (Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Research Topic Recommendation Based on Latent Dirichlet Allocation

AU - Chen, Hongshu

AU - Wang, Xuefeng

AU - Song, Yahui

AU - Wang, Ximeng

AU - Wang, Xiang

AU - Yu, Miaomiao

PY - 2019/11

Y1 - 2019/11

N2 - Knowledge discovery pushes every discipline, including bibliometrics and innovation management, to reposition itself and stay competitive. With the exponential growth of scientific literature, it has become increasingly difficult for researchers to quickly and effectively identify potential research topics in an interested area to advance their research. This has led to the development of research topic recommendation. In this paper, aiming to explore the potential author-topic relations in depth, we proposed a research topic recommendation methodology based on latent Dirichlet allocation and bipartite network analysis, to predict the inspiring research topics that an author potentially will be interested and working on. A case study on scientific literature in the area of knowledge discovery is then presented to demonstrate the feasibility of the methodology. The result of this research could assist academic researchers in identifying and extending potential research directions.

AB - Knowledge discovery pushes every discipline, including bibliometrics and innovation management, to reposition itself and stay competitive. With the exponential growth of scientific literature, it has become increasingly difficult for researchers to quickly and effectively identify potential research topics in an interested area to advance their research. This has led to the development of research topic recommendation. In this paper, aiming to explore the potential author-topic relations in depth, we proposed a research topic recommendation methodology based on latent Dirichlet allocation and bipartite network analysis, to predict the inspiring research topics that an author potentially will be interested and working on. A case study on scientific literature in the area of knowledge discovery is then presented to demonstrate the feasibility of the methodology. The result of this research could assist academic researchers in identifying and extending potential research directions.

KW - bipartite networks

KW - latent Dirichlet allocation

KW - link prediction

KW - topic modeling

UR - http://www.scopus.com/inward/record.url?scp=85091516799&partnerID=8YFLogxK

U2 - 10.1109/ISKE47853.2019.9170324

DO - 10.1109/ISKE47853.2019.9170324

M3 - Conference contribution

AN - SCOPUS:85091516799

T3 - Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019

SP - 637

EP - 643

BT - Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019

A2 - Zou, Li

A2 - Fang, Lingling

A2 - Fu, Bo

A2 - Niu, Panpan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019

Y2 - 14 November 2019 through 16 November 2019

ER -

Chen H , Wang X, Song Y, Wang X, Wang X, Yu M. Research Topic Recommendation Based on Latent Dirichlet Allocation. In Zou L, Fang L, Fu B, Niu P, editors, Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 637-643. 9170324. (Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019). doi: 10.1109/ISKE47853.2019.9170324

Research Topic Recommendation Based on Latent Dirichlet Allocation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this