Advertisement

Mining Automatic Speech Transcripts for the Retrieval of Problematic Calls

  • Frederik Cailliau
  • Ariane Cavet
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7817)

Abstract

In order to assure and to improve the quality of service, call center operators need to automatically identify the problematic calls in the mass of information flowing through the call center. Our method to select and rank those critical conversations uses linguistic text mining to detect sentiment markers on French automatic speech transcripts. The markers’ weight and orientation are used to calculate the semantic orientation of the speech turns. The course of a conversation can then be graphically represented with positive and negative curves. We have established and evaluated on a manually annotated corpus three heuristics for the automatic selection of problematic conversations. Two proved to be very useful and complementary for the retrieval of conversations having segments with anger and tension. Their precision is high enough for use in real world systems and the ranking evaluated by mean precision follows the usual relevance behavior of a search engine.

Keywords

Sentiment analysis conversational speech call center transcripts customer satisfaction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bazillon, T., Jousse, V., Béchet, F., Estève, Y., Linarès, G., Luzzati, D.: La parole spontanée : transcription et traitement. TAL 49(3), 47–76 (2008)Google Scholar
  2. 2.
    Cailliau, F., Cavet, A.: Analyse des sentiments et transcription automatique: modélisation du déroulement de conversations téléphoniques. TAL 51(3), 131–154 (2010)Google Scholar
  3. 3.
    Cailliau, F., Giraudel, A.: Enhanced Search and Navigation on Conversational Speech. In: Proc. of SSCS 2008, SIGIR 2008 Workshop, Singapour, pp. 66–70 (2008)Google Scholar
  4. 4.
    Charaudeau, P.: Grammaire du sens et de l’expression. Hachette Education, Paris (1992)Google Scholar
  5. 5.
    Chastagnol, C., Devillers, L.: Analysis of Anger across several agent-customer interactions in French call centers. In: ICASSP 2011, pp. 4960–4963 (2011)Google Scholar
  6. 6.
    Cieri, C., Miller, D., Walker, K.: The Fisher Corpus: a Resource for the Next Generations of Speech-to-Text. In: Proc. of LREC 2004, Lisbon, pp. 69–71 (2004)Google Scholar
  7. 7.
    Danesi, C., Clavel, C.: Impact of spontaneous speech features on business concept detection: a study of call-centre data. In: Proc. of SSCS 2010, pp. 11–14. ACM, New York (2010)Google Scholar
  8. 8.
    Devillers, L., Vaudable, C., Chastagnol, C.: Real-life emotion-related states detection in call centers: a cross-corpora study. In: INTERSPEECH 2010, pp. 2350–2353 (2010)Google Scholar
  9. 9.
    Galliano, S., Geoffrois, E., Mostefa, D., Choukri, K., Bonastre, J.-F., Gravier, G.: The ESTER Phase II Evaluation Campaign for the Rich Transcription of French Broadcast News. In: Proc. of Interspeech 2005, Lisbonne, pp. 1149–1152 (2005)Google Scholar
  10. 10.
    Galliano, S., Gravier, G., Chaubard, L.: The ESTER 2 evaluation campaign for the rich transcription of French radio broadcasts. In: Proc. of INTERSPEECH, Brighton, pp. 2583–2586 (2009)Google Scholar
  11. 11.
    Garnier-Rizet, M., Adda, G., Cailliau, F., Guillemin-Lanne, S., Waast, C.: CallSurf - Automatic transcription, indexing and structuration of call center conversational speech for knowledge extraction and query by content. In: Proc. of LREC 2008, Marrakech (2008)Google Scholar
  12. 12.
    Gavalda, M., Schlueter, J.: The truth is out there: Using advanced speech analytics to learn why customers call help-line desks and how effectively they are being served by the call center agent. In: Neustein, A. (ed.) Advances in Speech Recognition: Mobile Environments, Call Centers and Clinics, pp. 221–243. Springer (2010)Google Scholar
  13. 13.
    Gauvain, J.-L., Adda, G., Lamel, L., Lefèvre, F., Schwenk, H.: Transcription de la parole conversationnelle. TAL 45(3), 35–47 (2004)Google Scholar
  14. 14.
    Hastie, H.W., Prasad, R., Walker, M.: What’s the trouble: automatically identifying problematic dialogues in DARPA communicator dialogue systems. In: Proc. of ACL 2002, pp. 384–391. ACL, Stroudsburg (2002)Google Scholar
  15. 15.
    Mishne, G., Carmel, D., Hoory, R., Roytman, A., Soffer, A.: Automatic analysis of call-center conversations. In: Proc. of CIKM 2005, pp. 453–459. ACM, New York (2005)Google Scholar
  16. 16.
    Padmanabhan, D., Kummamuru, K.: Mining conversational text for procedures with applications in contact centers. Int. J. Doc. Anal. Recognit. 10(3), 227–238 (2007)CrossRefGoogle Scholar
  17. 17.
    Pallotta, V., Delmonte, R., Vrieling, L., Walker, D.: Interaction Mining: the new frontier of Call Center Analytics. In: Proc. of DART 2011, Palermo (2011)Google Scholar
  18. 18.
    Pang, B., Lee, L.: Opinion Mining and Sentiment Analysis. Found. Trends Inf. Retr. 2(1-2), 1–135 (2008)CrossRefGoogle Scholar
  19. 19.
    Roy, S., Subramaniam, L.V.: Automatic generation of domain models for call centers from noisy transcriptions. In: Proc. ACL 2006, pp. 737–744. ACL, Stroudsburg (2006)Google Scholar
  20. 20.
    Szöke, I., Burget, L., Černocký, J., Fapšo, M., Karafiát, M., Matějka, P., Schwarz, P.: Comparison of Keyword Spotting Approaches for Informal Continuous Speech. In: Proc. of INTERSPEECH 2005, Lisbon, pp. 633–636 (2005)Google Scholar
  21. 21.
    Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-Based Methods for Sentiment Analysis. Computational Linguistics 37(2), 267–307 (2011)CrossRefGoogle Scholar
  22. 22.
    Takeuchi, H., Subramaniam, L.V., Nasukawa, T., Roy, S.: Automatic identification of important segments and expressions for mining of bussiness-oriented conversations at contact centers. In: Proc. of EMNLP-CoNLL, pp. 458–467 (2007)Google Scholar
  23. 23.
    Tang, M., Pellom, B., Hacioglu, K.: Call-type Classification and Unsupervised Training for the Call Center Domain. In: IEEE-ASRU 2003. St. Thomas, US Virgin Islands (2003)Google Scholar
  24. 24.
    Tang, H., Tan, S., Cheng, X.: A survey on sentiment detection of reviews. Expert Systems with Applications 36(7), 10760–10773 (2009)CrossRefGoogle Scholar
  25. 25.
    Vaudable, C., Rollet, N., Devillers, L.: Annotation of Affective Interaction in Real-life Dialogs Collected in a Call-center. In: Proc. 3rd Intern. Workshop on Emotion, LREC 2010, Valletta, Malta (2010)Google Scholar
  26. 26.
    Ververidis, D., Kotropoulos, C.: Emotional Speech Recognition: Resources, Features, and Methods. Speech Communication 48, 1162–1181 (2006)CrossRefGoogle Scholar
  27. 27.
    Walker, M.A., Langkilde-Geary, I., Wright Hastie, H., Wright, J., Gorin, A.: Automatically Training a Problematic Dialogue Predictor for a Spoken Dialogue System. Journal of Artificial Intelligence Research 16, 293–319 (2002)zbMATHGoogle Scholar
  28. 28.
    Zweig, G., Siohan, O., Saon, G., Ramabhadran, B., Povey, D., Mangu, L., Kingsbury, B.: Automated quality monitoring for call centers using speech and NLP technologies. In: Proc. of NAACL-Demonstrations 2006, pp. 292–295. ACL, Stroudsburg (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Frederik Cailliau
    • 1
  • Ariane Cavet
    • 1
  1. 1.SinequaParisFrance

Personalised recommendations