Emotion Detection in Customer Care Narendra Gupta, Mazin Gilbert, and Giuseppe Di Fabbrizio AT&T Labs - Research, Inc ACL

Outline  [1.Introduction]  [2.Emotion detection in s] 2.1 Classifier 2.2 Feature extraction  [3.Annotation]  [4.Experiments and evaluation]

1.Introduction Emotional s often contain complaints about unfair treatment due to negligence, incompetence, rigid protocols, unfriendly systems, and unresponsive personnel. Reduce the churn i.e., retaining customers who otherwise would have taken their business elsewhere.

1.Introduction A negative emotional component articulated by phrases like: you suck, disgusted. Enumerating factual sentences such as: you overcharged, take my business elsewhere.

Outline  [1.Introduction]  [2.Emotion detection in s] 2.1 Classifier 2.2 Feature extraction  [3.Annotation]  [4.Experiments and evaluation]

2.Emotion detection in s We use supervised machine learning techniques to detect emotional s.

2.Emotion detection in s 2.1 Classifier We used Boostexter as text classification. The output of the final classifier f is: i.e., the sum of confidence of all classifiers The final classifier f can be mapped onto a confidence value between 0 and 1 by a logistic function;

2.Emotion detection in s 2.1 Classifier Training model:

2.Emotion detection in s 2.2 Feature extraction Salient features For our data we have identified the eight features listed below.

2.Emotion detection in s 2.2 Feature extraction

In the labeling guide for critical s labelers were instructed to look for salient features in the and keep a list of encountered phrases. We further enriched these lists by: a)using general knowledge of English, we added variations to existing phrases. b) searching a large body of text (different from testing) for different phrases in which key words from known phrases participated. For example from the known phrase lied to we used the word lied and found a phrase blatantly lied.

Outline  [1.Introduction]  [2.Emotion detection in s] 2.1 Classifier 2.2 Feature extraction  [3.Annotation]  [4.Experiments and evaluation]

3.Annotation 1) Two different labelers. 2) Kappa :

3.Annotation

Outline  [1.Introduction]  [2.Emotion detection in s] 2.1 Classifier 2.2 Feature extraction  [3.Annotation]  [4.Experiments and evaluation]

4.Experiments and evaluation We used cross validation (leave-one-out) technique on the test set.

4.Experiments and evaluation