Today, we live in a world where every time we turn on our smartphones, we are inextricably tied by data, laws and flowing bytes to different countries. A world in which personal expressions are framed and mediated by digital platforms, and where new kinds of currencies, financial exchange and even labor bypass corporations and governments. Simultaneously, the same technologies increase governmental powers of surveillance, allow corporations to extract ever more complex working arrangements and do little to slow the construction of actual walls along actual borders. On the one hand, the agency of individuals and groups is starting to approach that of nation states; on the other, our mobility and hard-won rights are under threat. What tools do we need to understand this world, and how can art assist in envisioning and enacting other possible futures?This publication investigates the new relationships between states, citizens and the stateless made possible by emerging technologies. It is the result of a two-year EU-funded collaboration between Aksioma (SI), Drugo More (HR), Furtherfield (UK), Institute of Network Cultures (NL), NeMe (CY), and a diverse range of artists, curators, theorists and audiences. State Machines insists on the need for new forms of expression and new artistic practices to address the most urgent questions of our time, and seeks to educate and empower the digital subjects of today to become active, engaged, and effective digital citizens of tomorrow.Contributors: James Bridle, Max Dovey, Marc Garrett, Valeria Graziano, Max Haiven, Lynn Hershman Leeson, Francis Hunger, Helen Kaplinsky, Marcell Mars, Tomislav Medak, Rob Myers, Emily van der Nagel, Rachel O’Dwyer, Lídia Pereira, Rebecca L. Stein, Cassie Thornton, Paul Vanouse, Patricia de Vries, Krystian Woznicki.
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%.
In this post I give an overview of the theory, tools, frameworks and best practices I have found until now around the testing (and debugging) of machine learning applications. I will start by giving an overview of the specificities of testing machine learning applications.
