DISCRN: A Distributed Storytelling Framework for Intelligence Analysis

Shukla, Manu; Santos, Raimundo F. Dos; Chen, Feng; Lu, Chang-Tien

doi:10.1089/big.2017.0025

Cited by 8 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Amazon, Uber, Airbnb, and Craigslist) into people's daily lives. Nevertheless, users on these design artifacts require more opportunities to generate their own stories and content with applications that are more likely digital storytelling (Kenney & Zysman, 2016; Shukla, Dos Santos, Chen, & Lu, 2017).…”

Section: Discussionmentioning

confidence: 99%

“StoryWeb”: A storytelling‐based knowledge‐sharing application among multiple stakeholders

2020

View full text Add to dashboard Cite

The research objective of this paper is to develop a storytelling-based knowledgesharing application that enables users to co-create their own stories for both individuals and groups. To address this, a design science research methodology was applied for elucidating users' requirements. As empirical evidence, a case study was conducted on the children's book industry to synthesize a knowledge-sharing design application named "StoryWeb". Usability tests were conducted to reconfigure users' feedback and suggestions after two StoryWeb prototypes were developed. This study makes three main contributions. First, it empirically tests individual's or group's creativity and co-creation by a view of knowledge sharing. Second, it methodologically applies a design thinking approach into a knowledge-sharing study. Third, it also practically suggests feasible guidelines for the creativity and innovation research community on which features of storytelling-based applications can be configured.

show abstract

Section: Discussionmentioning

confidence: 99%

“StoryWeb”: A storytelling‐based knowledge‐sharing application among multiple stakeholders

2020

View full text Add to dashboard Cite

show abstract

“…Keyword extraction has been widely used to discover associations between entities in a text, especially in social networks [23,36]. Shukla et al [11] presented DISCRN (distributed spatiotemporal Concept Search-based) to model spatiotemporal storytelling. This model uses concept search to link the entities extracted from microblogs and event data.…”

Section: Storytellingmentioning

confidence: 99%

“…A storytelling model can be used to analyze events or entities for different applications, such as event forecasting [20,21], intelligence analysts [11,14], and knowledge extraction [22]. A storytelling algorithm can generate relationships between entities, actors, or events [23,24] in the form of a graph, which then can be used as an abstraction for many applications.…”

Section: Related Workmentioning

confidence: 99%

“…A researcher searching for a specific topic in a relevant digital library may end up with thousands of documents to study for a literature review. Another scenario of a conventional search resulting in a massive information overflow is how intelligence analysts attempt to find information from a large number of news articles, field reports, and social media discussions [9][10][11][12]. In this paper, we present a storytelling algorithm that outlines a story as a chain of documents illustrating the evolution of an event.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CoRBS: A Dynamic Storytelling Algorithm using a Novel Contextualization Approach for Documents utilizing BERT Features

Nouri

Hossain

2023

Preprint

View full text Add to dashboard Cite

Storytelling is the process of connecting documents one after another representing the evolution of an event. Existing algorithms for storytelling connect events based on content overlaps between consecutive documents ignoring the role of the same term in different documents and the contemporary contexts (e.g., dynamic embeddings) of documents and terms. Due to the lack of role and contemporary contexts in the designs of the existing storytelling methods, the resultant stories frequently jump to documents with the keywords to form a chain but not a meaningful one. In this paper, we present a novel storytelling algorithm -- Contextual Role-Based Storytelling (CoRBS) -- that generates a chain of documents explaining the evolution of an event, addressing role and contemporary context issues of existing methods. CoRBS starts with a given document and moves forward temporally, stitching together role and context-driven documents to represent the evolution of the events that appear in the first document. We define the role of a term in a document as a distribution of similarities of the nearest neighbors of the term based on BERT-embeddings of all terms of that document. Contemporary contexts are incorporated as a mechanism to discover a coherent next document while the story progresses. Our experiments demonstrate that CoRBS generates more meaningful stories compared to other baseline storytelling techniques.

show abstract

“…3. The DERIV framework is a sequence of Spark jobs [26] that run on AWS (Amazon Web Services) EC2 (Elastic Compute Cloud) clusters and continues with storylines generated by DISCRN [27] based on traversing ConceptGraph [28]. It proceeds to build models from training data and storylines scores from testing data for a brand whose perception is being calculated.…”

Section: Architecturementioning

confidence: 99%