iVisClustering: An Interactive Visual Document Clustering via Topic Modeling

Lee, Han-Seung; Kihm, Jaeyeon; Choo, Jaegul; Stasko, John; Park, Haesun

doi:10.1111/j.1467-8659.2012.03108.x

Cited by 127 publications

(80 citation statements)

References 28 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…LeadLine is also a river-like visualization, but more emphasized on the bursting to topics hotness. iVisClustering [32] not only provides various visualization techniques for LDA model, but also enables users steering of LDA process. Besides applications in text analysis field, LDA model has been adopted in computer graphics and computer vision field [42,9,31] for various purposes, such as segmentation, classification, pattern recognition, etc.…”

Section: Topic Model and Lda Analysismentioning

confidence: 99%

FLDA: Latent Dirichlet Allocation Based Unsteady Flow Analysis

Fan

Lai

Guo

et al. 2014

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

In this paper, we present a novel feature extraction approach called FLDA for unsteady flow fields based on Latent Dirichlet allocation (LDA) model. Analogous to topic modeling in text analysis, in our approach, pathlines and features in a given flow field are defined as documents and words respectively. Flow topics are then extracted based on Latent Dirichlet allocation. Different from other feature extraction methods, our approach clusters pathlines with probabilistic assignment, and aggregates features to meaningful topics at the same time. We build a prototype system to support exploration of unsteady flow field with our proposed LDA-based method. Interactive techniques are also developed to explore the extracted topics and to gain insight from the data. We conduct case studies to demonstrate the effectiveness of our proposed approach.

show abstract

Section: Topic Model and Lda Analysismentioning

confidence: 99%

FLDA: Latent Dirichlet Allocation Based Unsteady Flow Analysis

Fan

Lai

Guo

et al. 2014

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…Lee y otros proponen en [11], un entorno visual interactivo para modelos de clustering, en un contexto de análisis de documentos de textos, y que genera grupos con base en las palabras que más se repiten.…”

Section: Trabajos Relacionadosunclassified

Visualización Interactiva para Modelos de Clústeres

Castillo-Rojas

Vega-Damke

2018

Ingeniare. Rev. chil. ing.

View full text Add to dashboard Cite

RESUMENEste artículo presenta el diseño e implementación de un nuevo esquema de visualización interactiva para modelos de clústeres denominado VIMC, en el contexto de un proceso de minería de datos. La visualización de un modelo de clústeres se torna compleja cuando el conjunto de datos es de alto volumen, densidad y dimensionalidad. El diseño del esquema VIMC se basa en cuatro características: visualización interactiva, combinación de modelos, artefactos gráficos ad-hoc, y uso de métricas. El objetivo de este esquema es contribuir al análisis y comprensión de un modelo de clústeres. Las métricas consideradas en este esquema propuesto, permiten comparar componentes de distintos clústeres, lo que a su vez ayuda a entender como se componen los grupos. A través de la implementación de un entorno visual web que reúne las características definidas en VIMC, y una evaluación en línea de 23 usuarios, donde se logran resultados positivos sobre la utilidad de este nuevo esquema de visualización.Palabras clave: Visualización de clústeres, visualización de modelos para minería de datos, visualización de minería de datos, visualización interactiva de modelos, esquemas de visualización de datos. ABSTRACT This paper presents the design and implementation of a new interactive visualization scheme for clustering models called VIMC, in the context of a data-mining process. The visualization models cluster becomes complex when the dataset is high volume, density and dimensionality. The design of VIMC

show abstract

“…We got 1418 nouns for JD online review and 5805 nouns for ZOL online reviews, which were used as features in the LDA model. We conducted the LDA model with four clusters [19] . The comparative analysis results…”

Section: Comparative Analysis Phasementioning

confidence: 99%

Comparative Analysis of Two Chinese Major Online Review Platforms in Customer Concern Identification

Jing¹,

Yan²

2017

Proceedings of the 2017 3rd International Conference on Economics, Social Science, Arts, Education and Management Engineering (

View full text Add to dashboard Cite

Abstract:Analysing online reviews is a good method to identify customers' needs and concerns. We conducted a comparative analysis of two Chinese major online review platforms (JD vs. ZOL) in customer concern identification using the LDA model. We find that there is a big difference between customer concerns of JD users and that of ZOL users. JD platform users pay more attention to sound quality, exterior, standby time, and performance, while ZOL platform users focus on function, configuration, brand, and tutorial. The former concentrates on specific attributes while the latter takes note of attributes in general and brand information. The results of this study are beneficial for retails to find target customer and for manufacturers to improve customer satisfaction.

show abstract

iVisClustering: An Interactive Visual Document Clustering via Topic Modeling

Abstract: Clustering plays an important role in many large

Cited by 127 publications

References 28 publications

FLDA: Latent Dirichlet Allocation Based Unsteady Flow Analysis

FLDA: Latent Dirichlet Allocation Based Unsteady Flow Analysis

Visualización Interactiva para Modelos de Clústeres

Comparative Analysis of Two Chinese Major Online Review Platforms in Customer Concern Identification

Contact Info

Product

Resources

About