Menu Close

Guided Topic Model Refinement using Word-Embedding Projections


Mennatallah El-Assady, Rebecca Kehlbeck, Christopher Collins, Daniel Keim, and Oliver Deussen

We present a framework that allows users to incorporate the semantics of their domain knowledge for topic model refinement while remaining model-agnostic. Our approach enables users to (1) understand the semantic space of the model, (2) identify regions of potential conflicts and problems, and (3) readjust the semantic relation of concepts based on their understanding, directly influencing the topic modelling. These tasks are supported by an interactive visual analytics workspace that uses word-embedding projections to define concept regions which can then be refined. The user-refined concepts are independent of a particular document collection and can be transferred to related corpora. All user interactions within the concept space directly affect the semantic relations of the underlying vector space model, which, in turn, change the topic modelling. In addition to direct manipulation, our system guides the users’ decision-making process through recommended interactions that point out potential improvements. This targeted refinement aims at minimizing the feedback required for an efficient human-in-the-loop process. We confirm the improvements achieved through our approach in two user studies that show topic model quality improvements through our visual knowledge externalization and learning process.


    [pods name="publication" id="4197" template="Publication Template (list item)" shortcodes=1]

Progressive Learning of Topic Modeling Parameters


Mennatallah El-Assady, Rita Sevastjanova, Fabian Sperrle, Daniel Keim, and Christopher Collins

Topic modelling algorithms are widely used to analyze the thematic composition of text corpora but remain difficult to interpret and adjust. Addressing these limitations, we present a modular visual analytics framework, tackling the understandability and adaptability of topic models through a user-driven reinforcement learning process that does not require a deep understanding of the underlying topic modelling algorithms. Given a document corpus, our approach initializes two algorithm configurations based on a parameter space analysis that enhances document separability. We abstract the model complexity in an interactive visual workspace for exploring the automatic matching results of two models, investigating topic summaries, analyzing parameter distributions, and reviewing documents. The main contribution of our work is an iterative decision-making technique in which users provide document-based relevance feedback that allows the framework to converge to a user-endorsed topic distribution. We also report feedback from a two-stage study which shows that our technique results in topic model quality improvements on two independent measures.

This research was given a Best VAST Paper Honorable Mention Award at VAST 2017.

To apply our technique on your own data or try out a demo, please visit (Individual accounts will be created upon request).

Demo Video

Talk from IEEE VAST 2017


    [pods name="publication" id="4245" template="Publication Template (list item)" shortcodes=1]