Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Using Conversational Software Agent for Information Retrieval at a Private Equity Firm
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2018 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

 Information retrieval and conversational software agents (CSA) have been two sub-fields of computer science that have grown exponentially and have had profound impact on companies. The aim of this study was to examine whether or not the implementation of CSA could improve information retrieval at a private equity firm. A CSA was constructed that utilizes a method known as named entity recognition to understand the input question by the user to retrieve the correct information. The results showed that the CSA was less time consuming compared to manually searching through data in a spreadsheet and that the standard deviation was lower. The time consumed and the standard deviation for manual searches were more depended on the location of the data in the spreadsheet. Despite that users found the CSA more efficient and convenient to use, there were several areas that could have been improved. The CSA did not understand follow-up questions, spelling mistakes and therefore, several users found that the software lacked key characteristics of CSA.

Place, publisher, year, edition, pages
2018. , p. 14
Series
TRITA-EECS-EX ; 2018:423
Keywords [en]
Conversational software agent, information retrieval, human-computer interaction, named entity recognition
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-249987OAI: oai:DiVA.org:kth-249987DiVA, id: diva2:1306757
Supervisors
Examiners
Available from: 2019-05-13 Created: 2019-04-24 Last updated: 2019-05-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 23 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf