1 / 17

Extending Live Chat Reference Service at University of Turin: A Case Study

Analyzing chat logs to enhance live chat service for UniTO libraries, focusing on Psychology at Kiesow library. Using text mining to filter and improve chat responses.

delkins
Download Presentation

Extending Live Chat Reference Service at University of Turin: A Case Study

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Università degli Studi di Torino Ufficio Servizi Bibliografici Digitali Maria Vittoria Muzzupapa Marco Stefano Tomatis Extending the live chat reference service at the University of Turin - a case study

  2. PREMISES • 2014 - UniTOstarted the service “TUTTO” with alive chat referenceintegrated in it • Patronsasked for virtualreference to exploit the UniTolibraryservices for bibliographicresearch • Analysis of chat logs from 2014 to 2016 wascarried out • Automatic editing of FAQ for the UniTO Library System Extending the live chat reference service at the University of Turin - a case study

  3. AIM OF THE PROJECT Respond to the question: Is the amount of live chat exchanges addressed to the UniTopsychology library F. Kiesow so consistent to require the activation of a dedicated chat instance on the Kiesow library website? Extending the live chat reference service at the University of Turin - a case study

  4. OPERATING CONTEXT The PsychologylibraryKiesowis part of the University of Turin“Polo delle Biblioteche Scientifiche” (scientificlibrarygroup) Extending the live chat reference service at the University of Turin - a case study

  5. OPERATING CONTEXT Polo delle Biblioteche Scientifiche: Human Movement Science Chemistry (Ponzio) Earth Science (Spezia andMalaroda) Informatics Physics Mathematics (Peano) Pharmacy (Guareschi) Biology Psychology (Kiesow) Extending the live chat reference service at the University of Turin - a case study

  6. CONTENT ANALYSIS How couldweanswer the projectquestion? Analysis of all the reference chat log files via text miningsolutions: • Automaticselection of chat fragmentstied to the differentlibraries of the Polo Scientifico by usingsubject-specifickeywords • Enumeration of the selectedtexts Extending the live chat reference service at the University of Turin - a case study

  7. CONTENT ANALYSIS Nextstep Furtherselection of all the Psychology-related chat exchanges by defininga newset of usefulkeywords Extending the live chat reference service at the University of Turin - a case study

  8. WHICH FILTERS? Keywordswerecarefullychosenaccording to the followingcriteria: • Institutional • Semantic Extending the live chat reference service at the University of Turin - a case study

  9. WHICH FILTERS? Institutionalcriteria: Keywordswhichexplicitlymention the Universityof TurinPsychologylibrary or itsresources e.g.: • “Kiesow” • “PsycArticles” • “PsycInfo” Extending the live chat reference service at the University of Turin - a case study

  10. WHICH FILTERS? Semanticcriteria: Keywordsexpressingspecificpsychologysubjects e.g.: • “Disturbo” (disturbance) • “Apprendimento” (learning) • “Disorder” Extending the live chat reference service at the University of Turin - a case study

  11. QUALITATIVE APPROACH Usage of READ Scale to define a set of taggingcodes to: Performfurthermanualanalysis to identify the differentskills the referencelibrarianisasked to exercise to reply patron requests Extending the live chat reference service at the University of Turin - a case study

  12. METHODOLOGICAL APPROACH • Save all chat sessions in CSV format log files • Merge all chat logsinto a single file Preliminary steps: Extending the live chat reference service at the University of Turin - a case study

  13. METHODOLOGICAL APPROACH Design of scripts for: • Removingadministrative and non-pertinent information • Delimiting each chat exchange via XML tags “<chat>…</chat>” • Tokenize the entire log file Extending the live chat reference service at the University of Turin - a case study

  14. TEXT MINING Design Regular Expressions into GAWK scripts for usingPattern Matchingfacility to Retrieveall the chat exchangesresponding to ourselectioncriteria - keywords Extending the live chat reference service at the University of Turin - a case study

  15. Extending the live chat reference service at the University of Turin - a case study

  16. Extending the live chat reference service at the University of Turin - a case study

  17. Extending the live chat reference service at the University of Turin - a case study

More Related