Lune

ACL Findings2023

Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections

Maria Leonor Pacheco, Tunazzina Islam, Lyle H. Ungar, Ming Yin, Dan Goldwasser

Abstract

Experts across diverse disciplines are often interested in making sense of large text collections. Traditionally, this challenge is approached either by noisy unsupervised techniques such as topic models, or by following a manual theme discovery process. In this paper, we expand the definition of a theme to account for more than just a word distribution, and include generalized concepts deemed relevant by domain experts. Then, we propose an interactive framework that receives and encodes expert feedback at different levels of abstraction. Our framework strikes a balance between automation and manual coding, allowing experts to maintain control of their study while reducing the manual effort required.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Effects of Collaboration on the Performance of Interactive Theme Discovery Systems cites Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence
  • Effects of Collaboration on the Performance of Interactive Theme Discovery Systems cites Identifying Morality Frames in Political Tweets using Relational Learning
  • ConceptCarve: Dynamic Realization of Evidence cites Natural Language Decompositions of Implicit Content Enable Better Text Representations
  • HICode: Hierarchical Inductive Coding with LLMs cites Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence
  • Framing in the Presence of Supporting Data: A Case Study in U.S. Economic News cites Identifying Morality Frames in Political Tweets using Relational Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. Natural Language Decompositions of Implicit Content Enable Better Text RepresentationsAlexander Miserlis Hoyle, Rupak Sarkar, Pranav Goel, Philip ResnikEMNLP 2023 · 3 citations
  2. Effects of Collaboration on the Performance of Interactive Theme Discovery SystemsAlvin Po-Chun Chen, Rohan Das, Dananjay Srinivas, Alexandra Barry et al.ACL 2026
  3. ConceptCarve: Dynamic Realization of EvidenceEylon Caplan, Dan GoldwasserACL 2025
  4. HICode: Hierarchical Inductive Coding with LLMsMian Zhong, Pristina Wang, Anjalie FieldEMNLP 2025
  5. Framing in the Presence of Supporting Data: A Case Study in U.S. Economic NewsAlexandria Leto, Elliot Pickens, Coen D. Needell, David Rothschild et al.ACL 2024

Builds on2

  1. Is Automated Topic Model Evaluation Broken? The Incoherence of CoherenceAlexander Miserlis Hoyle, Pranav Goel, Andrew Hian-Cheong, Denis Peskov et al.NeurIPS 2021 · 220 citations
  2. Identifying Morality Frames in Political Tweets using Relational LearningShamik Roy, Maria Leonor Pacheco, Dan GoldwasserEMNLP 2021 · 23 citations

Related papers

  1. CentaurTA: A Self-Improving Human-Agents Collaboration Framework for Thematic AnalysisLei Wang, Min Huang, Eduard C. DragutACL Findings 2026
  2. Coordinated Topic ModelingPritom Saha Akash, Jie Huang, Kevin Chen-Chuan ChangEMNLP 2022 · 2 citations
  3. Scholastic: Graphical Human-AI Collaboration for Inductive and Interpretive Text AnalysisMatt-Heun Hong, Lauren A. Marsh, Jessica L. Feuston, Janet Ruppert et al.UIST 2022 · 26 citations
  4. PaTAT: Human-AI Collaborative Qualitative Coding with Explainable Interactive Rule SynthesisSimret Araya Gebreegziabher, Zheng Zhang, Xiaohang Tang, Yihao Meng et al.CHI 2023 · 70 citations
  5. Understanding Interaction with Machine Learning through a Thematic Analysis Coding Assistant: A User StudyFederico Milana, Enrico Costanza, Mirco Musolesi, Amid AyobiCSCW 2025 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines