Jonathan Herzig

Predicting Customer Satisfaction in Customer Support Conversations in Social Media Using Affective Features

Providing customer support through social media channels is gaining popularity. In such a context, predicting customer satisfaction in an early stage of a service conversation is important. Such an analysis can help personalize agent assignment to maximize customer satisfaction, and prioritize conversations. In this paper, we show that affective features such as customers and agents personality traits and emotion expression improve prediction of customer satisfaction when added to more typical text based features. We only utilize information extracted from the first customer conversation turn and previous customer and agent social network activity. Thus, our customer satisfaction classifier outputs its prediction in an early stage of the conversation, before any interaction has taken place between the customer and an agent. Our model was trained and tested on a Twitter conversations dataset of two customer support services, and shows an improvement of 30% in F1-score for predicting dissatisfaction.

A statistical approach to mining customers' conversational data from social media

In this paper, we present one possible way of analyzing social media conversional data in order to better understand customers. Ultimately, our goal is to analyze customer behavior as it is expressed in free-form conversations and extract from it commercially valuable information about the customer. In this study, we concentrate on using statistical techniques for analyzing this unstructured data at two levels: 1) at the level of the words used in the conversation and 2) by mapping those words to abstract concepts. The goal of such a statistical analysis is twofold. First, the statistically significant terms used by the users and the concepts associated with them provide insight on a users interests that commercial services can use, for example, in order to target advertisements. In addition, knowing the evolution of a customers interests and hobbies can be exploited commercially by retailers, media and entertainment companies, telecommunications companies, and more. In this paper, we describe a general framework for the analysis of social media data and, in turn, the application of the framework to the statistical analysis of the language of tweets.

Classifying Emotions in Customer Support Dialogues in Social Media

Providing customer support through social media channels is gaining increasing popularity. In such a context, automatic detection and analysis of the emotions expressed by customers is important, as is identification of the emotional techniques (e.g., apology, empathy, etc.) in the responses of customer service agents. Result of such an analysis can help assess the quality of such a service, help and inform agents about desirable responses, and help develop automated service agents for social media interactions. In this paper, we show that, in addition to text based turn features, dialogue features can significantly improve detection of emotions in social media customer service dialogues and help predict emotional techniques used by customer service agents.

EHCTool: Managing Emotional Hotspots for Conversational Agents

Building conversational agents is becoming easier thanks to the profusion of designated platforms. Integrating emotional intelligence in such agents contributes to positive user satisfaction. Currently, this integration is implemented using calls to an emotion analysis service. In this demonstration we present EHCTool that aims to detect and notify the conversation designer about problematic conversation states where emotions are likely to be expressed by the user. Using its exploration view, the tool assists the designer to manage and define appropriate responses in these cases.

On the Expression of Agent Emotions in Customer Support Dialogs in Social Media

Providing customer support through social media channels is gaining popularity. In this context, it is important for the agent, either human or automated, to express emotions when needed. In this paper we study the patterns of human agents emotional expression and question the need of Affective NLG. By analyzing real dialogs that were tagged by the crowd, we show that emotional responses contribute to the quality of the dialog and relate to customer satisfaction, and that human agents express emotions by simply adding emotional acknowledgment at the beginning of the response.

Emotion Detection from Text via Ensemble Classification Using Word Embeddings

Emotion detection from text has become a popular task due to the key role of emotions in human-machine interaction. Current approaches represent text as a sparse bag-of-words vector. In this work, we propose a new approach that utilizes pre-trained, dense word embedding representations. We introduce an ensemble approach combining both sparse and dense representations. Our experiments include five datasets for emotion detection from different domains and show an average improvement of 11.6% in macro average F1-score.