Methods For Mining And Summarizing Text Conversations

Due to the Internet Revolution, human conversational data - in written forms - are accumulating in a phenomenal rate. Individuals and organizations engage in email exchanges, blogging, texting and other social media activities. The advances in natural language processing provide ample opportunities for these "informal documents" to be analyzed and mined, thus creating numerous new and valuable applications. This book presents a set of computational methods to extract features from conversational data, and to provide natural language summaries of the data. Specifically, in the first half of the book, we introduce extraction and mining methods for performing subjectivity and sentiment detection, topic segmentation and modeling, dialogue act recognition, decision and action item detection, and extraction of conversational structure. In the second half of the book, we focus on natural language summarization of conversational data. We describe several extractive and abstractive summarizers developed for various conversation modalities. We also describe attempts for building multi-modal summarizers.