Comparing Methods for Finding Search Sessions on a Specified Topic: A Double Case Study

Tessel Bogaard; Aysenur Bilgin; Jan Wielemaker; Laura Hollink; C R Ribbens; Jacco van Ossenbruggen

Comparing Methods for Finding Search Sessions on a Specified Topic: A Double Case Study

Tessel Bogaard, Aysenur Bilgin, Jan Wielemaker, Laura Hollink, C R Ribbens, Jacco van Ossenbruggen

NIOD Institute for War, Holocaust and Genocide studies

Research output: Chapter in book/volume › Contribution to conference proceedings › Scientific › peer-review

Abstract

Users searching for different topics in a collection may show distinct search patterns. To analyze search behavior of users searching for a specific topic, we need to retrieve the sessions containing this topic. In this paper, we compare different topic representations and approaches to find topic-specific sessions. We conduct our research in a double case study of two topics, World War II and feminism, using search logs of a historical newspaper collection. We evaluate the results using manually created ground truths of over 600 sessions per topic. The two case studies show similar results: The query-based methods yield high precision, at the expense of recall. The document-based methods find more sessions, at the expense of precision. In both approaches, precision improves significantly by manually curating the topic representations. This study demonstrates how different methods to find sessions containing specific topics can be applied by digital humanities scholars and practitioners.

Original language	English
Title of host publication	Linking Theory and Practice of Digital Libraries
Subtitle of host publication	25th International Conference on Theory and Practice of Digital Libraries, TPDL 2021, Virtual Event, September 13–17, 2021, Proceedings
Editors	Gerd Berget, Mark Michael Hall, Daniel Brenn, Sanna Kumpulainen
Place of Publication	New York
Publisher	Springer
Number of pages	14
ISBN (Electronic)	978-3-030-86324-1
ISBN (Print)	978-3-030-86323-4
Publication status	Published - 2021

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
ISSN (Print)	0302-9743

Keywords

Digital libraries
User interests
Log analysis
Word embeddings
Historical Topics
Wikipedia; Popular historical culture

Access to Document

https://hdl.handle.net/1871.1/0a1ee28b-be5d-4beb-972e-3b2e587dcf09Licence: Unspecified

Cite this

Bogaard, T., Bilgin, A., Wielemaker, J., Hollink, L., Ribbens, C. R., & van Ossenbruggen, J. (2021). Comparing Methods for Finding Search Sessions on a Specified Topic: A Double Case Study. In G. Berget, M. M. Hall, D. Brenn, & S. Kumpulainen (Eds.), Linking Theory and Practice of Digital Libraries: 25th International Conference on Theory and Practice of Digital Libraries, TPDL 2021, Virtual Event, September 13–17, 2021, Proceedings (Lecture Notes in Computer Science). Springer. https://hdl.handle.net/1871.1/0a1ee28b-be5d-4beb-972e-3b2e587dcf09

Bogaard, Tessel ; Bilgin, Aysenur ; Wielemaker, Jan et al. / Comparing Methods for Finding Search Sessions on a Specified Topic : A Double Case Study. Linking Theory and Practice of Digital Libraries: 25th International Conference on Theory and Practice of Digital Libraries, TPDL 2021, Virtual Event, September 13–17, 2021, Proceedings. editor / Gerd Berget ; Mark Michael Hall ; Daniel Brenn ; Sanna Kumpulainen. New York : Springer, 2021. (Lecture Notes in Computer Science).

@inbook{0dc8b8c66134457e831da30f9c2d2512,

title = "Comparing Methods for Finding Search Sessions on a Specified Topic: A Double Case Study",

abstract = "Users searching for different topics in a collection may show distinct search patterns. To analyze search behavior of users searching for a specific topic, we need to retrieve the sessions containing this topic. In this paper, we compare different topic representations and approaches to find topic-specific sessions. We conduct our research in a double case study of two topics, World War II and feminism, using search logs of a historical newspaper collection. We evaluate the results using manually created ground truths of over 600 sessions per topic. The two case studies show similar results: The query-based methods yield high precision, at the expense of recall. The document-based methods find more sessions, at the expense of precision. In both approaches, precision improves significantly by manually curating the topic representations. This study demonstrates how different methods to find sessions containing specific topics can be applied by digital humanities scholars and practitioners.",

keywords = "Digital libraries, User interests, Log analysis, Word embeddings, Historical Topics, Wikipedia; Popular historical culture",

author = "Tessel Bogaard and Aysenur Bilgin and Jan Wielemaker and Laura Hollink and Ribbens, {C R} and {van Ossenbruggen}, Jacco",

year = "2021",

language = "English",

isbn = "978-3-030-86323-4",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

editor = "Gerd Berget and Hall, {Mark Michael} and Daniel Brenn and Sanna Kumpulainen",

booktitle = "Linking Theory and Practice of Digital Libraries",

address = "Germany",

}

Bogaard, T, Bilgin, A, Wielemaker, J, Hollink, L, Ribbens, CR & van Ossenbruggen, J 2021, Comparing Methods for Finding Search Sessions on a Specified Topic: A Double Case Study. in G Berget, MM Hall, D Brenn & S Kumpulainen (eds), Linking Theory and Practice of Digital Libraries: 25th International Conference on Theory and Practice of Digital Libraries, TPDL 2021, Virtual Event, September 13–17, 2021, Proceedings. Lecture Notes in Computer Science, Springer, New York. <https://hdl.handle.net/1871.1/0a1ee28b-be5d-4beb-972e-3b2e587dcf09>

Comparing Methods for Finding Search Sessions on a Specified Topic: A Double Case Study. / Bogaard, Tessel; Bilgin, Aysenur; Wielemaker, Jan et al.
Linking Theory and Practice of Digital Libraries: 25th International Conference on Theory and Practice of Digital Libraries, TPDL 2021, Virtual Event, September 13–17, 2021, Proceedings. ed. / Gerd Berget; Mark Michael Hall; Daniel Brenn; Sanna Kumpulainen. New York: Springer, 2021. (Lecture Notes in Computer Science).

Research output: Chapter in book/volume › Contribution to conference proceedings › Scientific › peer-review

TY - CHAP

T1 - Comparing Methods for Finding Search Sessions on a Specified Topic

T2 - A Double Case Study

AU - Bogaard, Tessel

AU - Bilgin, Aysenur

AU - Wielemaker, Jan

AU - Hollink, Laura

AU - Ribbens, C R

AU - van Ossenbruggen, Jacco

PY - 2021

Y1 - 2021

N2 - Users searching for different topics in a collection may show distinct search patterns. To analyze search behavior of users searching for a specific topic, we need to retrieve the sessions containing this topic. In this paper, we compare different topic representations and approaches to find topic-specific sessions. We conduct our research in a double case study of two topics, World War II and feminism, using search logs of a historical newspaper collection. We evaluate the results using manually created ground truths of over 600 sessions per topic. The two case studies show similar results: The query-based methods yield high precision, at the expense of recall. The document-based methods find more sessions, at the expense of precision. In both approaches, precision improves significantly by manually curating the topic representations. This study demonstrates how different methods to find sessions containing specific topics can be applied by digital humanities scholars and practitioners.

AB - Users searching for different topics in a collection may show distinct search patterns. To analyze search behavior of users searching for a specific topic, we need to retrieve the sessions containing this topic. In this paper, we compare different topic representations and approaches to find topic-specific sessions. We conduct our research in a double case study of two topics, World War II and feminism, using search logs of a historical newspaper collection. We evaluate the results using manually created ground truths of over 600 sessions per topic. The two case studies show similar results: The query-based methods yield high precision, at the expense of recall. The document-based methods find more sessions, at the expense of precision. In both approaches, precision improves significantly by manually curating the topic representations. This study demonstrates how different methods to find sessions containing specific topics can be applied by digital humanities scholars and practitioners.

KW - Digital libraries

KW - User interests

KW - Log analysis

KW - Word embeddings

KW - Historical Topics

KW - Wikipedia; Popular historical culture

UR - https://www.springerprofessional.de/en/comparing-methods-for-finding-search-sessions-on-a-specified-top/19637216

M3 - Contribution to conference proceedings

SN - 978-3-030-86323-4

T3 - Lecture Notes in Computer Science

BT - Linking Theory and Practice of Digital Libraries

A2 - Berget, Gerd

A2 - Hall, Mark Michael

A2 - Brenn, Daniel

A2 - Kumpulainen, Sanna

PB - Springer

CY - New York

ER -

Bogaard T, Bilgin A, Wielemaker J, Hollink L, Ribbens CR, van Ossenbruggen J. Comparing Methods for Finding Search Sessions on a Specified Topic: A Double Case Study. In Berget G, Hall MM, Brenn D, Kumpulainen S, editors, Linking Theory and Practice of Digital Libraries: 25th International Conference on Theory and Practice of Digital Libraries, TPDL 2021, Virtual Event, September 13–17, 2021, Proceedings. New York: Springer. 2021. (Lecture Notes in Computer Science).

Comparing Methods for Finding Search Sessions on a Specified Topic: A Double Case Study

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Wikipedia’s World War II: Fragmenting the narrative?

Wikipedia: Een virtuele graadmeter voor de maatschappelijke rol van geschiedenis?

Cite this