Identification of class specific discourse patterns

Abstract

In this paper we address the problem of extracting important (and unimportant) discourse patterns from call center conversations. Call centers provide dialog based calling-in support for customers to address their queries, requests and complaints. A Call center is the direct interface between an organization and its customers and it is important to capture the voice-of-customer by gathering insights into the customer experience. We have observed that the calls received at a call center contain segments within them that follow specific patterns that are typical of the issue being addressed in the call. We present methods to extract such patterns from the calls. We show that by aggregating over a few hundred calls, specific discourse patterns begin to emerge for each class of calls. Further, we show that such discourse patterns are useful for classifying calls and for identifying parts of the calls that provide insights into customer behaviour.

Data-based research at IIT Bombay

“…By this we mean: constraints that can be imposed on features and structures without serious loss of expressive power; transformations of the featurediscovery problem to other tasks for which efficient algorithms are known; optimisation formulations that can be solved efficiently, learning and inferencing with structured output spaces and so on. We have pursued the following strategies: (a) pose the problem as a discrete optimisation problem and solve it heuristically [28,15,48,39,49], (b) pose the problem as a continuous (often convex) opti-misation problem with sparsity inducing regularizers and solves it optimally [27,36] and (c) study restrictions on the space of relational features and investigate empirically whether it is acceptable for a relational learner to examine a more restricted space of features than that actually necessary for the full statistical model [41,35,33] We have also looked at heuristics for speeding up inference algorithms in relational settings [34].…”

“…The purpose here is to investigate the applicability of feature-based techniques to data analysis tasks of constructing discriminatory and generative models for problems such as information extraction and disambiguation [33,15,48,39,49,50].…”

Automatically Extracting Dialog Models from Conversation Transcripts

“…These features are extracted from all utterances present in the transcripts by using the algorithm given in [11]. Agent and customer utterances are clustered separately.…”

“…have you rented a car from <a_rental_agency> before. We implemented an efficient algorithm described in [11] (an extension of the apriori algorithm [12]) for finding frequent patterns of non-consecutive tokens. The minSup value in apriori corresponds to the minimum number of times a non-consecutive n-gram should occur across all the sentences.…”

“…This is the fraction of documents in which the sequence s n occurs, where a maximum token gap of (δ) is allowed between each subsequent token of the sequence s n . The algorithm iteratively builds token-sequences of length n+1 from token sequences of length n. We refer the readers to [11] for the proof of optimality and further details.…”