MedLDA: maximum margin supervised topic models for regression and classification

Supervised topic models utilize document's side information for discovering predictive low dimensional representations of documents; and existing models apply likelihood-based estimation. In this paper, we present a max-margin supervised topic model for both continuous and categorical response variables. Our approach, the maximum entropy discrimination latent Dirichlet allocation (MedLDA), utilizes the max-margin principle to train supervised topic models and estimate predictive topic representations that are arguably more suitable for prediction. We develop efficient variational methods for posterior inference and demonstrate qualitatively and quantitatively the advantages of MedLDA over likelihood-based topic models on movie review and 20 Newsgroups data sets.

• Publication year

  2009

• Venue

  International Conference on Machine Learning

• Publication date

  2009-06-14

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1145/1553374.1553535
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Latent Dirichlet Allocation

  2009influential reference
• Partially Observed Maximum Entropy Discrimination Markov Networks

  2008cited by this paper
• Laplace maximum margin Markov networks

  2008cited by this paper
• DiscLDA: Discriminative Learning for Dimensionality Reduction and Classification

  2008influential reference
• Visualizing Data using t-SNE

  2008cited by this paper
• Supervised Topic Models

  2007cited by this paper
• Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification

  2006cited by this paper
• Correlated Topic Models

  2005cited by this paper
• A tutorial on support vector regression

  2004influential reference
• Exponential Family Harmoniums with an Application to Information Retrieval

  2004cited by this paper
• Finding scientific topics

  2004cited by this paper
• Modeling annotated data

  2003cited by this paper
• On the Algorithmic Implementation of Multiclass Kernel-based Vector Machines

  2002cited by this paper
• Making large-scale support vector machine learning practical

  1999cited by this paper
• Advances in kernel methods: support vector learning

  1999influential reference
• Making large scale SVM learning practical

  1998cited by this paper
• THIS IS A DRAFT VERSION. FINAL VERSION TO BE PUBLISHED AT NIPS ’06 A Collapsed Variational Bayesian Inference Algorithm for Latent Dirichlet Allocation

  year unknowncited by this paper

• Leveraging large language models to enhance clustering-based topic modeling

  2025cites this paper
• Exploring topic modelling: a comparative analysis of traditional and transformer-based approaches with emphasis on coherence and diversity

  2025cites this paper
• Polarization in Online Public Discourse

  2025cites this paper
• Beyond Labels and Topics: Discovering Causal Relationships in Neural Topic Modeling

  2024cites this paper
• BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction

  2024cites this paper
• A Neuro-symbolic Approach for Faceted Search in Digital Libraries

  2024cites this paper
• Supervised Neural Topic Modeling with Label Alignment

  2024cites this paper
• A review on authorship attribution in text mining

  2023influential citation
• Supervised probabilistic latent semantic analysis with applications to controversy analysis of legislative bills

  2023cites this paper
• The Effect of Monetary Incentives on Health Care Social Media Content: Study Based on Topic Modeling and Sentiment Analysis

  2022cites this paper
• A Large Scale Document-Term Matching Method Based on Information Retrieval

  2022cites this paper
• A supervised topic embedding model and its application

  2022cites this paper
• Max-Margin Deep Diverse Latent Dirichlet Allocation With Continual Learning

  2021influential citation
• Bayesian Text Classification and Summarization via A Class-Specified Topic Model

  2021cites this paper
• LDA Ensembles for Interactive Exploration and Categorization of Behaviors

  2020cites this paper
• Temporal tree representation for similarity computation between medical patients

  2020cites this paper
• Beyond the topics: how deep learning can improve the discriminability of probabilistic topic modelling

  2020cites this paper
• Drawing openness to experience from user generated contents: An interpretable data-driven topic modeling approach

  2020cites this paper
• Detection, analysis and prediction of traffic anomalies due to special events

  2020cites this paper
• NET-LDA: a novel topic modeling method based on semantic document similarity

  2020cites this paper
• Twin labeled LDA: a supervised topic model for document classification

  2020cites this paper
• Dynamic content based ranking

  2020cites this paper
• Online Bayesian max-margin subspace learning for multi-view classification and regression

  2019influential citation
• A Survey of Multi-Label Topic Models

  2019cites this paper
• Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification

  2019cites this paper
• Automatic Assessment of Complex Assignments using Topic Models

  2019cites this paper
• Efficient Analysis of Traffic Intersection Scenes by Employing Traffic Phase Information

  2019influential citation
• Rater-Effect IRT Model Integrating Supervised LDA for Accurate Measurement of Essay Writing Ability

  2019cites this paper
• Predicting taxi demand hotspots using automated Internet Search Queries

  2019cites this paper
• Quality assessment of Wikipedia content using topic models

  2019cites this paper
• Text Representation for Machine Learning Applications

  2019cites this paper
• Person Verification

  2019cites this paper
• IRT Topic Model for Essay Type Tests Using Rating Data and Text Information

  2019cites this paper
• Semi-supervised Deep Representation Learning for Multi-View Problems

  2018cites this paper
• Simultaneous Urban Region Function Discovery and Popularity Estimation via an Infinite Urbanization Process Model

  2018cites this paper
• Label Dependencies using a Tree-structured Hierarchy

  2018cites this paper
• Semi-Supervised Prediction-Constrained Topic Models

  2018influential citation
• Brain-wide Electrical Spatiotemporal Dynamics Encode Depression Vulnerability.

  2018cites this paper
• Text-Associated Max-Margin DeepWalk

  2018cites this paper
• Exploiting covariate embeddings for classification using Gaussian processes

  2018cites this paper
• Supervising topic models with Gaussian processes

  2018cites this paper
• Systematic identification of latent disease-gene associations from PubMed articles

  2018cites this paper
• Learning Topic Models by Neighborhood Aggregation

  2018influential citation
• Seed-Guided Topic Model for Document Filtering and Classification

  2018cites this paper
• Joint-Stochastic Spectral Inference for Robust Co-occurence Modeling and Latent Topic Analysis

  2018cites this paper
• Online Multi-label Text Classification using Topic Models

  2018cites this paper
• Document Labeling Using Source-LDA Combined with Correlation Matrix

  2018cites this paper
• Learning from Audience Intelligence: Dynamic Labeled LDA Model for Time-Sync Commented Video Tagging

  2018cites this paper
• A Survey of Statistical Topic Model for Multi-Label Classification

  2018cites this paper
• LF-LDA: A Supervised Topic Model for Multi-Label Documents Classification

  2018cites this paper
• Design and Empirical Evaluation of Interactive and Interpretable Machine Learning

  2018cites this paper
• The Historical Significance of Textual Distances

  2018cites this paper
• Neural Models for Documents with Metadata

  2017cites this paper
• Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey

  2017cites this paper
• Identifying prescription patterns with a topic model of diseases and medications

  2017cites this paper
• Automated Geocoding of Textual Documents: A Survey of Current Approaches

  2017influential citation
• LF-LDA: A Topic Model for Multi-label Classification

  2017cites this paper
• A Practical Guide to Sentiment Analysis

  2017cites this paper
• Recognizing human actions by two-level Beta process hidden Markov model

  2017cites this paper
• STExNMF: Spatio-Temporally Exclusive Topic Discovery for Anomalous Event Detection

  2017cites this paper
• Weakly supervised landslide detection using medlda regression model

  2017cites this paper
• Applications of Topic Models

  2017cites this paper
• Relation Prediction in Multilingual Data Based on Multimodal Relational Topic Models

  2017cites this paper
• Text mining and rating prediction with topical user models

  2017cites this paper
• Multi-label dataless text classification with topic modeling

  2017cites this paper
• Tone Analyzer for Online Customer Service: An Unsupervised Model with Interfered Training

  2017cites this paper
• Generative Models for Sentiment Analysis and Opinion Mining

  2017cites this paper
• Retrieving Semantically Similar Questions in Community Question Answering

  2017cites this paper
• Guided HTM: Hierarchical Topic Model with Dirichlet Forest Priors

  2017cites this paper
• Less is More: Learning Prominent and Diverse Topics for Data Summarization

  2016cites this paper
• ALTO: Active Learning with Topic Overviews for Speeding Label Induction and Document Labeling

  2016cites this paper
• Using internet search queries to predict human mobility in social events

  2016influential citation
• SaberLDA: Sparsity-Aware Learning of Topic Models on GPUs

  2016cites this paper
• Tourism activity recognition and discovery based on improved LDA model

  2016cites this paper
• Scene classification using class-supervised local-space-constraint latent Dirichlet allocation

  2016cites this paper
• Local–class–shared–topic latent Dirichlet allocation based scene classification

  2016cites this paper
• Cross-lingual link prediction using multimodal relational topic models

  2016cites this paper
• Multi-scale Spatial Topic Models for scene recognition

  2016influential citation
• Supervised Extraction of Usage Patterns in Different Document Representations

  2016cites this paper
• Infinite max-margin factor analysis via data augmentation

  2016cites this paper
• Structured Representation Using Latent Variable Models

  2016influential citation
• Locally Embedding Autoencoders: A Semi-Supervised Manifold Learning Approach of Document Representation

  2016cites this paper
• The Effects of the Content of FOMC Communications on US Treasury Rates

  2016influential citation
• On Effective Location-Aware Music Recommendation

  2016cites this paper
• Meshable: searching PubMed abstracts by utilizing MeSH and MeSH-derived topical terms

  2016cites this paper
• Predicting Socio-Economic Indicators using News Events

  2016cites this paper
• Activity Recognition in Smart Homes

  2016cites this paper
• Persian text classification based on topic models

  2016influential citation
• Inter-battery Topic Representation Learning

  2016cites this paper
• Disentangling Topic Models: A Cross-cultural Analysis of Personal Values through Words

  2016cites this paper
• Fast Supervised LDA for Discovering Micro-Events in Large-Scale Video Datasets

  2016cites this paper
• End-to-end Learning of LDA by Mirror-Descent Back Propagation over a Deep Architecture

  2015cites this paper
• Geocoding textual documents through the usage of hierarchical classifiers

  2015cites this paper
• Is Your Anchor Going Up or Down? Fast and Accurate Supervised Topic Models

  2015cites this paper
• Tag-Weighted Topic Model For Large-scale Semi-Structured Documents

  2015cites this paper
• Simultaneous Discovery of Common and Discriminative Topics via Joint Nonnegative Matrix Factorization

  2015cites this paper
• Binary Classifier Calibration Using a Bayesian Non-Parametric Approach

  2015cites this paper
• Knowledge Transfer Using Latent Variable Models

  2015cites this paper
• Welcome to the Party: Modeling the Topic Evolution of Political Parties in Microblogs Using Dynamic Topic Models

  2015cites this paper
• WITH LEARNING-TO-RANK TOPIC MODELING

  2015cites this paper