TaxonoMap: An Interactive System for the Exploration and Explanation of Unsupervised Large-Scale News Classification

Simon Ott; Daria Liakhovets; Mina Schütz; Medina Andresel; Moritz W. Rothmund-Burgwall; Armin Vogl; Heidi Scheichenbauer; Michael Suker; Alexander Schindler

TaxonoMap: An Interactive System for the Exploration and Explanation of Unsupervised Large-Scale News Classification

Simon Ott (Author and Speaker), Daria Liakhovets, Mina Schütz, Medina Andresel, Moritz W. Rothmund-Burgwall, Armin Vogl, Heidi Scheichenbauer, Michael Suker, Alexander Schindler

Data Science & Artifical Intelligence

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

Abstract

Creating analysis reports on events published in open source news data is a tedious task when done manually. Due to the large-scale nature of news data, analysts, such as government officials, often spend unnecessary resources when trying to research news data on a specific topic. In this paper, we present an interactive system for unsupervised classification of
news articles in a dynamic set of hierarchical labels. By providing users with explanations in the form of highlighted words, we enable them to quickly assess the relevance of an article to
a particular topic. We also provide aggregated visualisations to detect emerging events and include several quality-of-life enhancements such as a source rating mechanism and report
generation.

Original language	English
Title of host publication	CBMI 2024 21st International Conference on Content-Based Multimedia Indexing
Number of pages	4
Publication status	Published - 2024
Event	21st International Conference on Content-based Multimedia Indexing - Reykjavik University (RU), Reykjavik, Iceland Duration: 18 Sept 2017 → 20 Sept 2024 https://cbmi2024.org/

Conference

Conference	21st International Conference on Content-based Multimedia Indexing
Abbreviated title	CBMI 2024
Country/Territory	Iceland
City	Reykjavik
Period	18/09/17 → 20/09/24
Internet address	https://cbmi2024.org/

Research Field

Multimodal Analytics

A hybrid approach to Disinformation Detection
Schindler, A. (Speaker)
26 Mar 2024
Activity: Talk or presentation / Lecture › Invited talk at a scientific conference or institution

Cite this

@inproceedings{b8e13d43cc6b44c68b0c3bc0ad6c012b,

title = "TaxonoMap: An Interactive System for the Exploration and Explanation of Unsupervised Large-Scale News Classification",

abstract = "Creating analysis reports on events published in open source news data is a tedious task when done manually. Due to the large-scale nature of news data, analysts, such as government officials, often spend unnecessary resources when trying to research news data on a specific topic. In this paper, we present an interactive system for unsupervised classification ofnews articles in a dynamic set of hierarchical labels. By providing users with explanations in the form of highlighted words, we enable them to quickly assess the relevance of an article toa particular topic. We also provide aggregated visualisations to detect emerging events and include several quality-of-life enhancements such as a source rating mechanism and reportgeneration.",

author = "Simon Ott and Daria Liakhovets and Mina Sch{\"u}tz and Medina Andresel and Rothmund-Burgwall, {Moritz W.} and Armin Vogl and Heidi Scheichenbauer and Michael Suker and Alexander Schindler",

year = "2024",

language = "English",

booktitle = "CBMI 2024 21st International Conference on Content-Based Multimedia Indexing",

note = "21st International Conference on Content-based Multimedia Indexing, CBMI 2024 ; Conference date: 18-09-2017 Through 20-09-2024",

url = "https://cbmi2024.org/",

}

Ott, S , Liakhovets, D , Schütz, M , Andresel, M, Rothmund-Burgwall, MW, Vogl, A, Scheichenbauer, H, Suker, M & Schindler, A 2024, TaxonoMap: An Interactive System for the Exploration and Explanation of Unsupervised Large-Scale News Classification. in CBMI 2024 21st International Conference on Content-Based Multimedia Indexing . 21st International Conference on Content-based Multimedia Indexing, Reykjavik, Iceland, 18/09/17.

TaxonoMap: An Interactive System for the Exploration and Explanation of Unsupervised Large-Scale News Classification. / Ott, Simon (Author and Speaker); Liakhovets, Daria ; Schütz, Mina et al.
CBMI 2024 21st International Conference on Content-Based Multimedia Indexing . 2024.

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

TY - GEN

T1 - TaxonoMap: An Interactive System for the Exploration and Explanation of Unsupervised Large-Scale News Classification

AU - Liakhovets, Daria

AU - Schütz, Mina

AU - Andresel, Medina

AU - Rothmund-Burgwall, Moritz W.

AU - Vogl, Armin

AU - Scheichenbauer, Heidi

AU - Suker, Michael

AU - Schindler, Alexander

A2 - Ott, Simon

PY - 2024

Y1 - 2024

N2 - Creating analysis reports on events published in open source news data is a tedious task when done manually. Due to the large-scale nature of news data, analysts, such as government officials, often spend unnecessary resources when trying to research news data on a specific topic. In this paper, we present an interactive system for unsupervised classification ofnews articles in a dynamic set of hierarchical labels. By providing users with explanations in the form of highlighted words, we enable them to quickly assess the relevance of an article toa particular topic. We also provide aggregated visualisations to detect emerging events and include several quality-of-life enhancements such as a source rating mechanism and reportgeneration.

AB - Creating analysis reports on events published in open source news data is a tedious task when done manually. Due to the large-scale nature of news data, analysts, such as government officials, often spend unnecessary resources when trying to research news data on a specific topic. In this paper, we present an interactive system for unsupervised classification ofnews articles in a dynamic set of hierarchical labels. By providing users with explanations in the form of highlighted words, we enable them to quickly assess the relevance of an article toa particular topic. We also provide aggregated visualisations to detect emerging events and include several quality-of-life enhancements such as a source rating mechanism and reportgeneration.

M3 - Conference Proceedings with Oral Presentation

BT - CBMI 2024 21st International Conference on Content-Based Multimedia Indexing

T2 - 21st International Conference on Content-based Multimedia Indexing

Y2 - 18 September 2017 through 20 September 2024

ER -

TaxonoMap: An Interactive System for the Exploration and Explanation of Unsupervised Large-Scale News Classification

Abstract

Conference

Research Field

Fingerprint

Activities

A hybrid approach to Disinformation Detection

Cite this