Quick Evaluation of Research Impacts at Conferences Using SNS

Satoshi Fukuda, Hikaru Nakahashi, Hidetsugu Nanba, Toshiyuki Takezawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We are investigating ways of evaluating research impact as soon as possible after publication. Traditionally, the research impact or importance of academic journals has been evaluated using citation relations, such as the impact factor and the citation half-life. However, these citation-based methods require long periods to evaluate research impact and therefore are not suitable for evaluating the current impact of research papers at conferences. To solve this problem, we are studying the automatic evaluation of research impact using Twitter. Researchers participating in academic conferences often post their opinions or comments on Twitter. Here, research papers (presentations) that have many comments are considered to be outstanding and to have strong impact during the conference. In this paper, we propose a method for automatically aligning tweets with research papers. The procedure consists of the following three steps: (1) detecting valuable tweets, (2) aligning each valuable tweet with a research paper, and (3) calculating the research impact of each research paper by the number of aligned tweets. We conducted some experiments to confirm the effectiveness of our method. From the results, we obtained an MRR score of 0.223, which outperformed a baseline method.

Original languageEnglish
Title of host publicationProceedings - 26th International Workshop on Database and Expert Systems Applications, DEXA 2015
EditorsA Min Tjoa, Marcus Spies, Roland R. Wagner
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages259-263
Number of pages5
Volume2016-February
ISBN (Electronic)9781467375825
DOIs
Publication statusPublished - Feb 11 2016
Externally publishedYes
Event26th International Workshop on Database and Expert Systems Applications, DEXA 2015 - Valencia, Spain
Duration: Sep 1 2015Sep 4 2015

Other

Other26th International Workshop on Database and Expert Systems Applications, DEXA 2015
CountrySpain
CityValencia
Period9/1/159/4/15

Fingerprint

Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Fukuda, S., Nakahashi, H., Nanba, H., & Takezawa, T. (2016). Quick Evaluation of Research Impacts at Conferences Using SNS. In A. M. Tjoa, M. Spies, & R. R. Wagner (Eds.), Proceedings - 26th International Workshop on Database and Expert Systems Applications, DEXA 2015 (Vol. 2016-February, pp. 259-263). [7406303] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DEXA.2015.64

Quick Evaluation of Research Impacts at Conferences Using SNS. / Fukuda, Satoshi; Nakahashi, Hikaru; Nanba, Hidetsugu; Takezawa, Toshiyuki.

Proceedings - 26th International Workshop on Database and Expert Systems Applications, DEXA 2015. ed. / A Min Tjoa; Marcus Spies; Roland R. Wagner. Vol. 2016-February Institute of Electrical and Electronics Engineers Inc., 2016. p. 259-263 7406303.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fukuda, S, Nakahashi, H, Nanba, H & Takezawa, T 2016, Quick Evaluation of Research Impacts at Conferences Using SNS. in AM Tjoa, M Spies & RR Wagner (eds), Proceedings - 26th International Workshop on Database and Expert Systems Applications, DEXA 2015. vol. 2016-February, 7406303, Institute of Electrical and Electronics Engineers Inc., pp. 259-263, 26th International Workshop on Database and Expert Systems Applications, DEXA 2015, Valencia, Spain, 9/1/15. https://doi.org/10.1109/DEXA.2015.64
Fukuda S, Nakahashi H, Nanba H, Takezawa T. Quick Evaluation of Research Impacts at Conferences Using SNS. In Tjoa AM, Spies M, Wagner RR, editors, Proceedings - 26th International Workshop on Database and Expert Systems Applications, DEXA 2015. Vol. 2016-February. Institute of Electrical and Electronics Engineers Inc. 2016. p. 259-263. 7406303 https://doi.org/10.1109/DEXA.2015.64
Fukuda, Satoshi ; Nakahashi, Hikaru ; Nanba, Hidetsugu ; Takezawa, Toshiyuki. / Quick Evaluation of Research Impacts at Conferences Using SNS. Proceedings - 26th International Workshop on Database and Expert Systems Applications, DEXA 2015. editor / A Min Tjoa ; Marcus Spies ; Roland R. Wagner. Vol. 2016-February Institute of Electrical and Electronics Engineers Inc., 2016. pp. 259-263
@inproceedings{5d581637782d4d49a3d123a73a8fa24c,
title = "Quick Evaluation of Research Impacts at Conferences Using SNS",
abstract = "We are investigating ways of evaluating research impact as soon as possible after publication. Traditionally, the research impact or importance of academic journals has been evaluated using citation relations, such as the impact factor and the citation half-life. However, these citation-based methods require long periods to evaluate research impact and therefore are not suitable for evaluating the current impact of research papers at conferences. To solve this problem, we are studying the automatic evaluation of research impact using Twitter. Researchers participating in academic conferences often post their opinions or comments on Twitter. Here, research papers (presentations) that have many comments are considered to be outstanding and to have strong impact during the conference. In this paper, we propose a method for automatically aligning tweets with research papers. The procedure consists of the following three steps: (1) detecting valuable tweets, (2) aligning each valuable tweet with a research paper, and (3) calculating the research impact of each research paper by the number of aligned tweets. We conducted some experiments to confirm the effectiveness of our method. From the results, we obtained an MRR score of 0.223, which outperformed a baseline method.",
author = "Satoshi Fukuda and Hikaru Nakahashi and Hidetsugu Nanba and Toshiyuki Takezawa",
year = "2016",
month = "2",
day = "11",
doi = "10.1109/DEXA.2015.64",
language = "English",
volume = "2016-February",
pages = "259--263",
editor = "Tjoa, {A Min} and Marcus Spies and Wagner, {Roland R.}",
booktitle = "Proceedings - 26th International Workshop on Database and Expert Systems Applications, DEXA 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Quick Evaluation of Research Impacts at Conferences Using SNS

AU - Fukuda, Satoshi

AU - Nakahashi, Hikaru

AU - Nanba, Hidetsugu

AU - Takezawa, Toshiyuki

PY - 2016/2/11

Y1 - 2016/2/11

N2 - We are investigating ways of evaluating research impact as soon as possible after publication. Traditionally, the research impact or importance of academic journals has been evaluated using citation relations, such as the impact factor and the citation half-life. However, these citation-based methods require long periods to evaluate research impact and therefore are not suitable for evaluating the current impact of research papers at conferences. To solve this problem, we are studying the automatic evaluation of research impact using Twitter. Researchers participating in academic conferences often post their opinions or comments on Twitter. Here, research papers (presentations) that have many comments are considered to be outstanding and to have strong impact during the conference. In this paper, we propose a method for automatically aligning tweets with research papers. The procedure consists of the following three steps: (1) detecting valuable tweets, (2) aligning each valuable tweet with a research paper, and (3) calculating the research impact of each research paper by the number of aligned tweets. We conducted some experiments to confirm the effectiveness of our method. From the results, we obtained an MRR score of 0.223, which outperformed a baseline method.

AB - We are investigating ways of evaluating research impact as soon as possible after publication. Traditionally, the research impact or importance of academic journals has been evaluated using citation relations, such as the impact factor and the citation half-life. However, these citation-based methods require long periods to evaluate research impact and therefore are not suitable for evaluating the current impact of research papers at conferences. To solve this problem, we are studying the automatic evaluation of research impact using Twitter. Researchers participating in academic conferences often post their opinions or comments on Twitter. Here, research papers (presentations) that have many comments are considered to be outstanding and to have strong impact during the conference. In this paper, we propose a method for automatically aligning tweets with research papers. The procedure consists of the following three steps: (1) detecting valuable tweets, (2) aligning each valuable tweet with a research paper, and (3) calculating the research impact of each research paper by the number of aligned tweets. We conducted some experiments to confirm the effectiveness of our method. From the results, we obtained an MRR score of 0.223, which outperformed a baseline method.

UR - http://www.scopus.com/inward/record.url?scp=84962220270&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962220270&partnerID=8YFLogxK

U2 - 10.1109/DEXA.2015.64

DO - 10.1109/DEXA.2015.64

M3 - Conference contribution

VL - 2016-February

SP - 259

EP - 263

BT - Proceedings - 26th International Workshop on Database and Expert Systems Applications, DEXA 2015

A2 - Tjoa, A Min

A2 - Spies, Marcus

A2 - Wagner, Roland R.

PB - Institute of Electrical and Electronics Engineers Inc.

ER -