1887

n Suid-Afrikaanse Tydskrif vir Natuurwetenskap en Tegnologie - Oopbronintelligensie (OSINT) vir veiligheidsdoeleindes : die ontwikkeling van ’n dataontledingspyplyn om relevante WhatsAppboodskappe te ontleed - oorspronklike navorsing

Volume 38 Number 1
  • ISSN : 0254-3486
  • E-ISSN: 2222-4173

Abstract

Oopbronintelligensie het in die laaste paar dekades die dominante intelligensiedissipline geword. Die inligtingsontploffing het egter daartoe gelei dat geoutomatiseerde metodes aangewend moet word om inligting uit groot hoeveelhede data, wat gereeld in ’n ongestruktureerde formaat bestaan en deurlopend gegeneer word, te onttrek. Boonop het nuwe inligtingskanale soos sosiale media ontstaan wat beteken dat nie slegs die hoofstroommedia gemonitor kan word om gebeurtenisse te identifiseer nie. Hierdie artikel bespreek hoe ’n dataversamelings en -ontledingspyplyn saamgestel kan word om inligting uit WhatsApp boodskappe, wat op groepe met hul eie sienings van veiligheidsbegrippe of probleme voorkom, en onder meer verwys na gewelddadige betogings, plaasaanvalle, grondgrype en ander misdaad in Suid-Afrika, te onttrek. Daar word bespreek hoe teks skoongemaak word en gebeurtenisse en plekname onttrek word en dan outomaties na ’n visuele en interaktiewe gebruikerskoppelvlak uitgevoer word om die voorkoms van hierdie gebeurtenisse in kleiner areas of sektore en later landswyd te kan monitor. Uitdagings en probleme word bespreek, sowel as verdere navorsingsgeleenthede, wat insluit om so ’n stelsel met veiligheidheidsreaksiemagte soos die Polisiediens se databasisse te integreer ten einde waardevolle reaksie vir die gemeenskap ten opsigte van veiligheid te weeg te bring.


Open Source Intelligence (OSINT) for security purposes: Developing a data analysis pipeline to analyse relevant WhatsApp messages: Open source intelligence has become the dominant intelligence discipline over the past few decades. However, the information explosion has led to a need for automated methods to be used to extract information from large amounts of data, which is often in an unstructured format and continuously generated. In addition, new information channels such as social media have emerged which mean that not only the mainstream media can be monitored to identify events. This article discusses how a data collection and analysis pipeline can be compiled for extracting information from WhatsApp messages, which appear on groups that focus on security concepts or problems, and refer, inter alia, to violent protests, farm attacks, land grabs and other crime in South Africa. It discusses how to clean text and extract events and place names, and then automatically exports the results to a visual and interactive user interface to monitor the occurrence of these events in smaller areas or sectors and later nationwide. Challenges and problems are discussed, as well as further research opportunities, which include integrating such a system with security response forces such as the Police Service’s databases in order to provide valuable response for the community in terms of safety.

Loading full text...

Full text loading...

Loading

Article metrics loading...

/content/journal/10520/EJC-1710e4963d
2019-01-01
2019-10-18

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error