Interpretation and trust: designing model-driven visualizations for text analysis

By Jason Chuang, Daniel Ramage, Christopher D. Manning, Jeffrey Heer. International Conference on Human Factors in Computing Systems, 2012

294 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/98e3e60d90d421c1c29018911d6ede0160d68fcc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Termite: visualization techniques for assessing textual topic models (2012, background): “Model outputs often need to be verified by domain experts and modified [5] to ensure they correspond to meaningful concepts in the domain of analysis.”
Sequence Synopsis: Optimize Visual Summary of Temporal Event Data (2018, background): “[6], we show explicitly the co-occurrence of all the events with a focus event in the visualization.”
Full-Text or Abstract? Examining Topic Coherence Scores Using Latent Dirichlet Allocation (2017, methodology): “This two-dimensional representation is obtained by computing the distance between topics [41] and applying multidimensional scaling [42].”
LDAvis: A method for visualizing and interpreting topics (2014, methodology): “A pair of overlaid bars represent both the corpus-wide frequency of a given term as well as the topic-speciﬁc frequency of the term, as in (Chuang et al., 2012b).”
Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, methodology): “visualization techniques for text analysis [34, 35], tools to support interactive data analysis [24, 25, 37] and interactive machine learning [82].”
A Model of Text for Experimentation in the Social Sciences (2016, background): “…are an important part of the process, we also believe that recent work in the automated visualization of topic models (Chaney and Blei 2012; Chuang et al. 2012b; Chuang,Manning, andHeer 2012a) is of equal or greater importance for helping users to substantively engage with the underling…”
Green, circular, bio economy: A comparative analysis of sustainability avenues (2017, background): “The specificity of the keyword is calculated as the ratio of the frequency of the keyword in a certain topic to the overall keyword frequency in the overall corpus (Chuang et al., 2012), given aweight parameter l (0 l 1).”
Computational Grounded Theory: A Methodological Framework (2020, background): “While sociologists have found topic modeling helpful, these algorithms have come under a lot of criticism outside of sociology for their inaccuracy, exceedingly naive assumptions, and poor predictive performance (Chuang et al. 2012, 2013; Lancichinetti et al. 2014).”