Research Picks – April 2017

Engendered biometrics

Computerised gender recognition could be useful in physiological and psychological analysis as well as in security applications. However, there are difficulties in accurately classifying a human face as being of one particular gender, particular with reference to shape, facial features and behaviour. Researchers from the US and The Netherlands have reviewed the state of the art in gender recognition software. Despite the obstacles, the team found that biological information using physiological signals is not easily confused in its classification and has a higher accuracy (approximately 92 to 100%) compared with gender classification methods that do not use this approach. Biometrics are 80 to 99% accurate, less invasive and are not confused by mood nor clothing. Gender classification based on social network behaviour is least accurate (67 to 88.6%). “A single approach cannot satisfy all the gender classification requirements in various conditions, and each gender classification approach is suitable in a particular field according to the characteristic of performance,” the team reports.

Lin, F., Wu, Y., Zhuang, Y., Long, X. and Xu, W. (2016) ‘Human gender classification: a review’, Int. J. Biometrics, Vol. 8, Nos. 3/4, pp.275–300.

The morning sun really shows your age

The pattern of wrinkles in the aging human face is as unique as a fingerprint and as such might be useful in age-based intelligent systems for the applications such as biometrics, security and surveillance, according to researchers in India. The team has developed a novel human age classification system based on local binary patterns and wrinkle analysis for ageing feature extraction and multi-class support vector machine for age classification to classify the face images into four age classes. They report an accuracy in age classification of more than 91% even with “noisy” images of the human face when they apply their “salt-and-pepper” noise filter, although there is room for improvement in terms of extraction after filtering for Gaussian noise.

Jagtap, J. and Kokare, M. (2017) ‘Local binary patterns and wrinkle analysis in combination with multi-class support vector machine for human age classification’, Int. J. Applied Pattern Recognition, Vol. 4, No. 1, pp.1–13.

Twitter complexity

Researchers in Germany explain that almost every analysis of social media and social networking sites inevitably fails to take into account the complexity of human beings when investigating the properties of systems such as the microblogging platform, Twitter. They have now demonstrated that behaviour is a key feature in detecting users with specific characteristics. Their research demonstrates how meaningful patterns of user behaviour can be extracted on a large-scale that reflects the personalities of those users. “This,” the team suggests, “is a first step to prediction of user action and the underlying individual decision-making process.” Their approach identifies clusters methodically but allows for automated detection of user behaviour patterns.

Klotz, C., Akinalp, C. and Unger, H. (2016) ‘Clustering user behaviour patterns on Twitter’, Int. J. Social Network Mining, Vol. 2, No. 3, pp.203–223.

Virtual security

A virtual machine (VM) emulates the behaviour of a computer system. VMs are based on computer architecture and mimic the functionality of a physical computer. They are widely used in a range of settings not least cloud computing, to allow users to run operating systems meant for one kind of computer architecture on another, and to allow several systems to run on a single server independently. US researchers have looked at the security of VMs in the context of cloud computing and suggest that several bad practices ought to be corrected in order to tighten security in many systems. Risk-management plans and appropriate auditing represent the baseline if providers are to protect their systems from intruders, malware and other computer security problems.

Khan, A. (2017) ‘Virtual machine security’, Int. J. Information and Computer Security, Vol. 9, Nos. 1/2, pp.49–84.

Employers! You’re having a laugh, aren’t you?

Can humour on social media help managers find the most appropriate candidates for the job vacancies they hope to fill? Writing in the International Journal of Internet Marketing and Advertising, researchers from Finland, suggest that humorous recruitment campaigns can increase exposure for a given job advertisement but conversely the approach might lead to flippant applications at which point it might be difficult to separate the serious candidate from an inappropriate one. The team also suggests that choosing a particular social media channel over another may skew the type of applicants they receive for a given job, for better or worse.

Eeva-Liisa Oikarinen of Oulu Business School and Jaakko Sinisalo of Oulu University of Applied Sciences have carried out a case study of the social media recruitment campaign of a high-profile company operating in the architecture industry. The campaign used amusing text and graphics to entice people to apply for a specific vacancy and to differentiate the company from others in the market for job applicants.

The use of humour in consumer marketing is well known, indeed humour in marketing is probably as old as selling itself. However, in marketing an employment vacancy has been little used and advertising of jobs tends to be a rather dry affair. The team points out that where it has been used little research has been done to track the pros and cons. There is the potential, as with any marketing, for humour to be a double edged sword, the team suggests, with it having the potential to harm a company’s credibility and reputation if the humour is misplaced or causes offence.

Conversely, the humorous campaign can backfire if a responsive candidate is found and yet the work environment does not fit the jocular image projected. Moreover, some serious candidates perfectly suitable for the job may be put off from applying by the flippant nature of the campaign.

Oikarinen, E-L. and Sinisalo, J. (2017) ‘Personality or skill: a qualitative study of humorous recruitment advertising campaign on social media’, Int. J. Internet Marketing and Advertising, Vol. 11, No. 1, pp.22–43.

Emergency retweets in times of disaster

Twitter and other social media tools are commonly used around the world. Now, many government and not-for-profit organizations have a presence on at least one of these systems and use them in various ways to share information about their activities and engage with people.

For organizations that work in disaster zones and emergency situations, these tools can also be used to coordinate activities, help raise funds and disseminate timely news that can help in relief efforts. New research from the Department of Political Science at Sam Houston State University in Huntsville, Texas, USA, suggests that just half of the Red Cross and Red Crescent national societies around the world have adopted Twitter. They assessed the factors influencing adoption rates as well as message type and frequency, and the ability to reach large audiences. Writing in the International Journal of Emergency Management the researchers report that adoption is constrained by the digital divide and country population size. The team defines the digital divide as the disparity between country-level internet access rates.

Moreover, the researchers, Clayton Wukich and Ashish Khemka, found, the existence of an account on Twitter does not necessarily mean that the target audience is necessarily aware of its existence or engaging with it. There are significant limitations to organizational reach and many people who need to receive important content on a timely basis may not actually do so. However, the team observed high activity rates in countries such as Kenya, Indonesia, and the Philippines, which they say indicates the potential for continued growth in developing economies, especially as internet access increases.

The researchers recommend several strategies based on their findings that could help organizations improve their reach and engagement. For instance, they suggest that organizations must plan to make personnel available for handling social media throughout and subsequent to any large-scale disaster. At the technical level, organizations should use hashtags in order to expose their messages to the largest possible audience and to create some coherency during particular disasters. The team also found that while a link to additional information might be useful the presence of a link, a URL, actually reduced the rate at which Twitter users shared a particular update, it correlated negatively with retweets, in other words.

Wukich, C. and Khemka, A. (2017) ‘Social media adoption, message content, and reach: an examination of Red Cross and Red Crescent national societies’, Int. J. Emergency Management, Vol. 13, No. 2, pp.89-116.