2019
DOI: 10.1016/j.bdr.2019.04.003
|View full text |Cite
|
Sign up to set email alerts
|

Interactive Visual Analytics for Sensemaking with Big Text

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
19
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
5
4
1

Relationship

3
7

Authors

Journals

citations
Cited by 18 publications
(19 citation statements)
references
References 13 publications
0
19
0
Order By: Relevance
“…Another study [49] managed to narrow the 1,25 million results for one keyword to 131 759 blog posts for all keywords by using a specialized search engine. When key terms do not occur simultaneously, arranging terms under topics can help to find relevant documents [56,62]. Although a lot of research on online health communities (OHC) has used a manual content analysis approach, the approach becomes quickly unfeasible when the volume increases.…”
Section: Finding Relevant Datamentioning
confidence: 99%
“…Another study [49] managed to narrow the 1,25 million results for one keyword to 131 759 blog posts for all keywords by using a specialized search engine. When key terms do not occur simultaneously, arranging terms under topics can help to find relevant documents [56,62]. Although a lot of research on online health communities (OHC) has used a manual content analysis approach, the approach becomes quickly unfeasible when the volume increases.…”
Section: Finding Relevant Datamentioning
confidence: 99%
“…SI's ability to infer the analyst's reasoning process is fundamentally limited by the feature space of the underlying machine learning. Text analytics systems with SI, such as ForceSPIRE [4,12] and Cosmos [9], typically use keywords (such as text terms and phrases) as data features (SI keyword in Fig. 1a), known as bag-ofwords [31].…”
Section: Semantic Interaction With Word Embeddingsmentioning
confidence: 99%
“…Quantitative tools such as Dis-Function [11] present similarity-based projections of the data, with a user interest weight vector applied to the dimensions of the dataset to influence the projection in response to user interactions. These learning techniques also support text data, as seen in systems like StarSPIRE [9,82] and Cosmos [24]. One key change for the text case is creating a similarity computation based on a distance metric such as Cosine distance to resolve issues with term sparcity [78] or Gower distance to adjust for missing terms [37].…”
Section: Dimension Reduction and Clustering Toolsmentioning
confidence: 99%