From web crawled text to project descriptions: automatic summarizing of social innovation projects

Nikola Milošević; Dimitar Marinov; Abdullah Gӧk; Goran Nenadic

doi:10.1007/978-3-030-23281-8_13

From web crawled text to project descriptions: automatic summarizing of social innovation projects

Nikola Milošević, Dimitar Marinov, Abdullah Gӧk, Goran Nenadic

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

83 Downloads (Pure)

Abstract

In the past decade, social innovation projects have gained the attention of policy makers, as they address important social issues in an innovative manner. A database of social innovation is an important source of information that can expand collaboration between social innovators, drive policy and serve as an important resource for research. Such a database needs to have projects described and summarized. I this paper, we propose and compare several methods (e.g. SVM-based, recurrent neural network based, ensambled) for describing projects based on the text that is available on project websites. We also address and propose a new metric for automated evaluation of summaries based on topic modelling.

Original language	English
Title of host publication	24th International Conference on Applications of Natural Language to Information Systems
Publisher	Springer Nature
DOIs	https://doi.org/10.1007/978-3-030-23281-8_13
Publication status	E-pub ahead of print - 21 Jun 2019
Event	24th International Conference on Applications of Natural Language to Information Systems - University of Salford, MediaCityUK Campus, Salford, United Kingdom Duration: 26 Jun 2019 → 28 Jun 2019

Conference

Conference	24th International Conference on Applications of Natural Language to Information Systems
Abbreviated title	NLDB2019
Country/Territory	United Kingdom
City	Salford
Period	26/06/19 → 28/06/19

Keywords

Summarization
evaluation metrics
text mining
natural language processing
social innovation
SVM
neural networks

Research Beacons, Institutes and Platforms

Manchester Institute of Innovation Research

Access to Document

10.1007/978-3-030-23281-8_13

Summarization_paperAccepted author manuscript, 235 KB

Cite this

@inproceedings{26e3507ca2d64b448086efdb06935baa,

title = "From web crawled text to project descriptions: automatic summarizing of social innovation projects",

abstract = "In the past decade, social innovation projects have gained the attention of policy makers, as they address important social issues in an innovative manner. A database of social innovation is an important source of information that can expand collaboration between social innovators, drive policy and serve as an important resource for research. Such a database needs to have projects described and summarized. I this paper, we propose and compare several methods (e.g. SVM-based, recurrent neural network based, ensambled) for describing projects based on the text that is available on project websites. We also address and propose a new metric for automated evaluation of summaries based on topic modelling.",

keywords = "Summarization, evaluation metrics, text mining, natural language processing, social innovation, SVM, neural networks",

author = "Nikola Milo{\v s}evi{\'c} and Dimitar Marinov and Abdullah Gӧk and Goran Nenadic",

year = "2019",

month = jun,

day = "21",

doi = "10.1007/978-3-030-23281-8_13",

language = "English",

booktitle = "24th International Conference on Applications of Natural Language to Information Systems",

publisher = "Springer Nature",

address = "United States",

note = "24th International Conference on Applications of Natural Language to Information Systems, NLDB2019 ; Conference date: 26-06-2019 Through 28-06-2019",

}

Milošević, N, Marinov, D, Gӧk, A & Nenadic, G 2019, From web crawled text to project descriptions: automatic summarizing of social innovation projects. in 24th International Conference on Applications of Natural Language to Information Systems. Springer Nature, 24th International Conference on Applications of Natural Language to Information Systems, Salford, United Kingdom, 26/06/19. https://doi.org/10.1007/978-3-030-23281-8_13

From web crawled text to project descriptions: automatic summarizing of social innovation projects. / Milošević, Nikola; Marinov, Dimitar; Gӧk, Abdullah et al.
24th International Conference on Applications of Natural Language to Information Systems. Springer Nature, 2019.

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

TY - GEN

T1 - From web crawled text to project descriptions: automatic summarizing of social innovation projects

AU - Milošević, Nikola

AU - Marinov, Dimitar

AU - Gӧk, Abdullah

AU - Nenadic, Goran

PY - 2019/6/21

Y1 - 2019/6/21

N2 - In the past decade, social innovation projects have gained the attention of policy makers, as they address important social issues in an innovative manner. A database of social innovation is an important source of information that can expand collaboration between social innovators, drive policy and serve as an important resource for research. Such a database needs to have projects described and summarized. I this paper, we propose and compare several methods (e.g. SVM-based, recurrent neural network based, ensambled) for describing projects based on the text that is available on project websites. We also address and propose a new metric for automated evaluation of summaries based on topic modelling.

AB - In the past decade, social innovation projects have gained the attention of policy makers, as they address important social issues in an innovative manner. A database of social innovation is an important source of information that can expand collaboration between social innovators, drive policy and serve as an important resource for research. Such a database needs to have projects described and summarized. I this paper, we propose and compare several methods (e.g. SVM-based, recurrent neural network based, ensambled) for describing projects based on the text that is available on project websites. We also address and propose a new metric for automated evaluation of summaries based on topic modelling.

KW - Summarization

KW - evaluation metrics

KW - text mining

KW - natural language processing

KW - social innovation

KW - SVM

KW - neural networks

U2 - 10.1007/978-3-030-23281-8_13

DO - 10.1007/978-3-030-23281-8_13

M3 - Conference contribution

BT - 24th International Conference on Applications of Natural Language to Information Systems

PB - Springer Nature

T2 - 24th International Conference on Applications of Natural Language to Information Systems

Y2 - 26 June 2019 through 28 June 2019

ER -

From web crawled text to project descriptions: automatic summarizing of social innovation projects

Abstract

Conference

Keywords

Research Beacons, Institutes and Platforms

Access to Document

Fingerprint

Cite this