Search results

Digital Tailspin

Privacy, copyright, classified documents and state secrets, but also spontaneous network phenomena like flash mobs and hashtag revolutions, reveal one thing – we lost control over the digital world. We experience a digital tailspin, or as Michael Seemann calls it in this essay: a loss of control or Kontrollverlust. Data we never knew existed is finding paths that were not intended and reveals information that we would never have thought of on our own. Traditional institutions and concepts of freedom are threatened by this digital tailspin. But that doesn’t mean we are lost. A new game emerges, where a different set of rules applies. To take part, we need to embrace a new way of thinking and a radical new ethics – we need to search for freedom in completely different places. While the Old Game depended upon top-down hierarchies and a trust in the protective power of state justice systems, the New Game asks you to let go of all these certainties. Strategies to play the game of digital tailspin rely on flexibility, openness, transparency and what is dubbed ‘antifragility’. In Digital Tailspin: Ten Rules for the Internet After Snowden Michael Seemann examines which strategies are most appropriate in the New Game and why.

Automatic Measurement of Corporate Reputation for Retail Companies from Online Public Data on the Web

Retail industry consists of the establishment of selling consumer goods (i.e. technology, pharmaceuticals, food and beverages, apparels and accessories, home improvement etc.) and services (i.e. specialty and movies) to customers through multiple channels of distribution including both the traditional brickand-mortar and online retailing. Managing corporate reputation of retail companies is crucial as it has many advantages, for instance, it has been proven to impact generated revenues (Wang et al., 2016). But, in order to be able to manage corporate reputation, one has to be able to measure it, or, nowadays even better, listen to relevant social signals that are out there on the public web. One of the most extensive and widely used frameworks for measuring corporate reputation is through conducting elaborated surveys with respective stakeholders (Fombrun et al., 2015). This approach is valuable but deemed to be laborious and resource-heavy and will not allow to generate automatic alerts and quick and live insights that are extremely needed in this era of internet. For these purposes a social listening approach is needed that can be tailored to online data such as consumer reviews as the main data source. Online review datasets are a form of electronic Word-of-Mouth (WOM) that, when a data source is picked that is relevant to retail, commonly contain relevant information about customers’ perceptions regarding products (Pookulangara, 2011) and that are massively available. The algorithm that we have built in our application provides retailers with reputation scores for all variables that are deemed to be relevant to retail in the model of Fombrun et al. (2015). Examples of such variables for products and services are high quality, good value, stands behind, and meets customer needs. We propose a new set of subvariables with which these variables can be operationalized for retail in particular. Scores are being calculated using proportions of positive opinion pairs such as <fast, delivery> or <rude, staff> that have been designed per variable. With these important insights extracted, companies can act accordingly and proceed to improve their corporate reputation. It is important to emphasize that, once the design is complete and implemented, all processing can be performed completely automatic and unsupervised. The application makes use of a state of the art aspect-based sentiment analysis (ABSA) framework because of ABSA’s ability to generate sentiment scores for all relevant variables and aspects. Since most online data is in open form and we deliberately want to avoid labelling any data by human experts, the unsupervised aspectator algorithm has been picked. It employs a lexicon to calculate sentiment scores and uses syntactic dependency paths to discover candidate aspects (Bancken et al., 2014). We have applied our approach to a large number of online review datasets that we sampled from a list of 50 top global retailers according to National Retail Federation (2020), including both offline and online operation, and that we scraped from trustpilot, a public website that is well-known to retailers. The algorithm has carefully been evaluated by manually annotating a randomly sampled subset of the datasets for validation purposes by two independent annotators. The Kappa’s score on this subset was 80%.

‘That others may die’

As heavily reported by media in May 2018, Google announced that it won’t renew its contract with the US Defense Department for an artificial intelligence endeavor known as Project Maven. The tech giant took the decision amidst a widespread public backlash and multiple employee resignations. Google was assigned to provide an AI-powered image labeler that would allow the Pentagon to browse a ‘Google-Earth-like’ drone system, according to one of the emails leaked during the scandal.

The perception of teachers on usability and accessibility of programming materials for children with visual impairments

In-Situ Water Quality Observations under a Large-Scale Floating Solar Farm Using Sensors and Underwater Drones

The rapid implementation of large scale floating solar panels has consequences to water quality and local ecosystems. Environmental impacts depend on the dimensions, design and proportions of the system in relation to the size of the surface water, as well as the characteristics of the water system (currents, tidal effects) and climatic conditions. There is often no time (and budget) for thorough research into these effects on ecology and water quality. A few studies have addressed the potential impacts of floating solar panels, but often rely on models without validation with in situ data. In this work, water quality sensors continuously monitored key water quality parameters at two different locations: (i) underneath a floating solar park; (ii) at a reference location positioned in open water. An underwater drone was used to obtain vertical profiles of water quality and to collect underwater images. The results showed little differences in the measured key water quality parameters below the solar panels. The temperature at the upper layers of water was lower under the solar panels, and there were less detected temperature fluctuations. A biofouling layer on the floating structure was visible in the underwater images a few months after the construction of the park

Improving Guidance Information by means of Metric Optical Flow onboard an UAS PP eindpresentatie

To better control the growing process of horticulture plants greenhouse growers need an automated way to efficiently and effectively find where diseases are spreading.The HiPerGreen project has done research in using an autonomous quadcopter for this scouting. In order for the quadcopter to be able to scout autonomously accurate location data is needed. Several different methods of obtaining location data have been investigated in prior research. In this research a relative sensor based on optical flow is looked into as a method of stabilizing an absolute measurement based on trilateration. For the optical flow sensor a novel block matching algorithm was developed. Simulated testing showed that Kalman Filter based sensor fusion of both measurements worked to reduce the standard deviation of the absolute measurement from 30 cm to less than 1 cm, while drift due to dead-reckoning was reduced to a maximum of 11 cm from over 36 cm.