Exploratory Data Analysis (EDA) provides guidance to users to help them refine their needs and find items of interest in large volumes of structured data. In this paper, we develop GUIDES, a framework for guided Text-based Item Exploration (TIE). TIE raises new challenges: (𝑖) the need to abstract and query textual data and (𝑖𝑖) the need to combine queries on both structured and unstructured content. GUIDES represents text dimensions such as sentiment and topics, and introduces new text-based operators that are seamlessly integrated with traditional EDA operators. To train TIE policies, it relies on a multi-reward function that captures different textual dimensions, and extends the Deep Q-Networks (DQN) architecture with multi-objective optimization. Our experiments on Amazon and IMDb, two real-world datasets, demonstrate the necessity of capturing fine-grained text dimensions, the superiority of using both text-based and attribute-based operators over attribute based operators only, and the need for multi-objective optimization.