Context Map Analysis of Consumer Voice on Social Media: A Contextualized Visualization Approach
Mining qualitative factors of online reviews that determine the readers’ perceived helpfulness, such as consumers’ narratives and styles, is essential for understanding the factors influencing consumers’ decision-making process in an online environment. In order to understand the essential qualitative factors in text, text visualization is often used as a tool by decision-makers to extract and study the most important aspects of a massive amount of unstructured information. Visualization tools in text analytics are typically based on content analysis, using n-gram frequencies or topic models which output commonly used words, phrases, or topics in a text corpus. However, the interpretation of these visual output and summary labels can be incomplete or misleading when words or phrases are taken out of context. In this talk, we present a network-based text visualization and natural language processing model that combines the connections of n-grams and distributed representations of text to understand the qualitative factors that determine the helpfulness of online product reviews. We use a novel Context Map approach to create a connected network of n-grams by considering the frequency in which they are used together in the same context. We combine network optimization techniques with embedded representation models to generate a more friendly and accurate interpretation potential visualization interface. Our approach provides a rich context analysis of the language used in online reviews.
Dr. Sukhwa Hong (email@example.com) is an Assistant Professor of Management Information Systems and Data Science, College of Business and Economics at University of Hawai’i at Hilo. He received his Ph.D. in Business Information Technology from Virginia Tech. His research interests include natural language processing, text analytics, social media analytics, text visualization, information economics, and computational linguistics.