Analysis of #FeesMustFall tweets reveals startling trends

December 15, 2016



Source: htxt.africa

 

Cyber security firm Snode has taken a look at tweets sorrounding recent #FeesMustFall protests and found some incredibly interesting data.

Earlier this year Snode launched a cyber security solution which uses machine learning and algorithms to detect patterns and anomalies in a network.

We’ve learned that Snode is quite good at detecting patterns so the team decided to see what sort of patterns they could find while analysing tweets related to #FeesMustFall.

This was done by looking at a few things namely; location of tweets and tweets using the #FeesMustFall hashtag.

 

So what did they find?

Looking at the locations of tweets Snode found that many tweets about Wits University originated from Pretoria. This Snode says contrasted against the subject of the tweets analysed.

Snode also found that users in Pretoria referenced Wits University 14 times more than the University of Pretoria.

Another interesting revelation was that of those users in the capital only 3% of #FeesMustFall tweets came from users linked to the Wits University account.

The vast majority of tweets referencing the institution – 94% to be precise – were sent from accounts that have political ties.

This, says Snode reveals that the #FeesMustFall protests may have been adopted by social media users to draw attention away from the goals of students.

 

Data in pictures

Snode says that by further analysing the meta-data in photos shared on Twitter there exists the potential to glean even more data such as the location the photo was taken (using GPS co-ordinates), the type of device the person was using and even a user’s real name.

But it doesn’t end there according to Snode co-founder Nithen Naidoo.

“There are a host of AI applications available, such as Russia’s FindFace, which allows users to scan a digital image of someone and then discover their online profile. There are therefore a number of tools on hand to benefit law enforcement as much as they do criminals,” said Naidoo.

This analysis shows us that you can’t inherently trust everything you read on social media, and perhaps we should be more questioning of what we see rather than sharing something because we think it’s topical.

Deep analysis of social media can also help those in positions of power make more informed decisions about what the public sentiment really is.

“With regard to socially relevant topics such as the student protests, having cyber intelligence at work can assist in gleaning vital insight,” says the co-founder.

“At Snode, we believe having such knowledge can not only help us understand the climate better, but also assist law enforcement and government services to predict and respond to critical events more efficiently,” Naidoo concluded.

Previous

Cyber intelligence reveals #FeesMustFall agenda

December 13, 2016

Source: gadget.co.za   Cyber intelligence and analytics specialist, Snode, recently used its tools to analyse the #FeesMustFall protest and delve deeper within Twitter, offering enriched insight beyond 140 characters. Social media platforms such as Twitter may be divisive, but its significance cannot be overlooked. Cyber intelligence and analytics specialist, Snode, believes the potential applications for social media are yet to be fully realised. “As a source of intelligence, Twitter is a valuable source of intelligence and it should be utilised by business and law enforcement. It is an open-source data-rich platform and needs to be leveraged in the best way possible,” notes CIO and co-founder of Snode, Nithen Naidoo. Using the recent #FeesMustFall protests as a case study to showcase the enriched capabilities of cyber intelligence, Snode was able to apply its analytical tools to delve deeper into the anatomy of the Tweets, and even discover that outside influencers were making an impact. The university fee protests are a hot topic of conversation in South Africa. The dialogue is been most prevalent on Twitter, where numerous messages have been exchanged under the guise of creating a discourse around the cost of tertiary education. Interestingly though, Snode’s analysts have unearthed some other key insights not obvious to most people.   Delving deeper To gain a deeper understanding of the underlying forces driving the #FeesMustFall protests, Snode analysts have fused various social media conversations to identify emerging trends associated with, and patterns of behaviour fuelling, this massive campaign. The most telling finding is that many of the tweets did not originate from the same location that the message was referencing. In particular, the majority of tweets mentioning the University of Witwatersrand were found to have been sent from Pretoria, nearly 65 kilometres away. In fact, Snode detected an anomaly in which tweets from South Africa’s capital with the #FeesMustFall hashtag referenced Wits 14 times more than they did in their own city’s university protest. Accompanying this anomaly was the fact that only 3% of #FeesMustFall tweets came from users linked to the @WitsUniversity handle, as opposed to a staggering total of 94% from politically affiliated Twitter accounts. According to Naidoo, it can be inferred that there was another agenda being played out, and the #FeesMustFall protests are being abused by some social media users to draw attention to other topics, ultimately misrepresenting the true aim of students.   True potential While the potential for social media to be misused by a small percentage of users, Snode says that victims of crime and law enforcement have the ability to fight back. The company’s real time processing for example, can dissect a myriad of information contained within a Tweet, including a Twitter user’s (real) name, origin of the Tweet (longitude and latitude), device type (iPhone or Android), and place of residence (e.g. city or hometown). “If users share an image on Twitter for example, the metadata contained within that photo can offer us a wide ranging array of insights,” says Naidoo. “There are a host of AI applications available, such as Russia’s FindFace, which allows users to scan a digital image of someone and then discover their online profile. There are therefore a number of tools on hand to benefit law enforcement as much as they do criminals,” he continued. In the right hands, this kind of machine assisted analytics can empower social media platforms such as Twitter to help make data-driven decisions, notes Naidoo. In the US, a number of American agencies are already using deep analysis within Twitter to track down dissidents, according to Saudi scientist Hala Al-Dosari in a recent interview with Bloomberg Businessweek. “South Africa needs to use available technology correctly, especially when it comes to tackling issues like crime within the country. With regard to socially relevant topics such as the student protests, having cyber intelligence at work can assist in gleaning vital insight. At Snode, we believe having such knowledge can not only help us understand the climate better, but also assist law enforcement and government services to predict and respond to critical events more efficiently,” says Naidoo.

Next

Security Summit 2017 announces its first Hackathon

February 23, 2017

Source: ITWeb   ITWeb Events, ICT skills development company Geekulcha and cyber security start-up Snode are bringing the first ever hackathon to the ITWeb Security Summit 2017. #SS17HACK is now open for registration and is looking for young, talented individuals who want to develop their skills through learning and innovation, and who have a passion for information security. According to Allyson Towle, conference director from ITWeb, the hackathon is challenging disruptive innovators to build the most secure systems possible, and will also be used to explore new innovative mechanisms for the security sector.   Skills development Tiyani Nghonyama, COO of Geekulcha, says: "As far as Security Summit 2017 is concerned, Geekulcha is highly anticipating a skills development drive through the hackathon especially for intermediate developers. We want to instill a culture of consciousness in information security from both the developers and consumers/users of digital solutions." According to him, the hackathon presents the perfect opportunity to discover new talent and valuable skills capacity for various organisations. "We want to send a strong message that there is a need to invest in the collaborative economy and peer-learning platforms such as hackathons." With this in mind, various organisations have been invited to scout talent for work and collaborative opportunities at this event. Nghonyama says the hackathon is hosted against the backdrop of a need to grow skills capacity in cyber security in the country. "We believe building the momentum and equipping fresh talent with critical knowledge, and being exposed to over 500 experts in the ITWeb Security Summit, is a first step towards winning the war as intended." He says it is a collective responsibility to insure innovation capacity continues to grow but grow safely and securely. "We have outlined three key sectors, namely finance, retail and public sector, that need critical defence, and we aim to build 'digital troops' through the hackathon." There will only be 30 spots available, and those wishing to apply need to choose from a number of themes, or suggest their own idea during the registration process. As part of the event, an 'ideathon' will be held on 22 April 2017 where the various stakeholders will make their final selection.   'Must be solved' ideas The mentors and judges have selected a few 'must be solved' ideas: Financial Sector An Artificial Intelligence (AI) and cognitive fraud detection system. Propose a model and system architecture for cheaply but safely distributing pension pay-outs to people in rural areas. Design and develop an OTP system for Internet Banking that doesn't require the use of a mobile phone. Public Sector Twitter intelligence solution. Blockchain voting system. Retail IOT cashless no-point of sale solution. Other Design and develop a system that will note whether your mobile phone is in the vicinity when you log onto your computer and deny access if it isn't.   Judging and prizes Judging for the hackathon will take place around 3pm on 17 May 2017, and the winners will be announced to the audience at around 5pm. The judges and mentors for the event include Dino Covotsos from Telspace Systems, Dr Jabu Mtsweni from the CSIR, Marc Silver from Discovery Health, Grant Thompson from MTN, Ivan Regasek from ITWeb, and Yugan Reddy from InfoGuardian. There will be a first prize of R20k, a second price of R10k and third prize of R5k. In addition, entrants stand a chance of being a recipient of one of a number of internships on offer by reputable organisations.