Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Chattbotar som verktyg för att förbättre kundtjänst inom e-handel
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2017 (Swedish)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Customer service via social media is becoming an increasingly prevalent phenomena, as are customer expectations for companies to embody service via social media. These expectations are part of a global trend of digitalization that includes digitalization of customer service. Hence, chatbots within customer service is an interesting subject. This study aims to examine whether chatbots, developed through chatbot platfonns, can be a complement for resolving simple customer service issues within e-commerce. The studied problems are evaluated with a user study. A test group often people took part in a series of case studies where they actively engaged with platform based chatbots developed in Wit.ai and Api.ai. The test group evaluated the performance of the chatbot in terms of qualitative and quantitative feedback. The result shows that the test group would prefer having access to a customer service chatbot while awaiting regular human customer service. However, the test group were negatively inclined to shop from an e-commerce store that provided customer service only through chatbots. The conclusion is that e-commerce stores should integrate chatbots as a complement to existing human customer service where the chatbots are available for customers while awaiting human customer service. More extensive studies should be done to examine greater use of chatbots in e-commerce stores.

Abstract [sv]

Det blir allt vanligare att konsumenter förväntar sig att företag erbjuder kundtjänst via sociala medier. Dessa förväntningar ar en del av en global digitaliseringstrend s0111 inkluderar digitalisering av kundtjänst. Av den anledningen blir chattbotar i kundtjänsten ett intressant ämne. Mot bakgrund av detta ämnar denna studie att undersoka huruvida plattformsutvecklade chattbotar kan vara ett komplement till enkla kundtjänstärenden inom e-handel.Frågeställningen utvärderas med hjälp av en anvandarstudie. En testgrupp på tio personer deltog i ett antal olika anvandarfall där de fick interagera med en plattformutvecklad chattbot från Wit.ai respektive Api.ai. I samband med anvandarstudien fick testpersonerna själva utvärdera chattbotarnas prestanda i kvantitativa och kvalitativa termer. Resultatet visar att testpersonerna skulle vilja ha tillgång till en kundtjänst-chattbot i väntan på mänsklig chattagent. Däremot var testpersonerna negativt inställda till att handla från en e-handelsbutik med uteslutande kundtjänst via chattbotar.Slutsatsen ar att e-handelsbutiker bor integrera chattbotar som ett komplement till mänsklig kundtjänst där chattbotar ar tillgängliga i väntan på mänsklig kundtjänst. Vid önskan att tillfredsstalla större kundtjänstbehov bör chattbotplattformar utforskas vidare.

Place, publisher, year, edition, pages
2017.
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-237945OAI: oai:DiVA.org:kth-237945DiVA, id: diva2:1259667
Examiners
Available from: 2018-10-30 Created: 2018-10-30 Last updated: 2018-10-30Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Computer Science and Communication (CSC)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 277 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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