This paper presents a Decision Support System (DSS) that helps companies with corporate reputation (CR) estimates of their respective brands by collecting provided feedbacks on their products and services and deriving state-of-the-art key performance indicators. A Sentiment Analysis Engine (SAE) is at the core of the proposed DSS that enables to monitor, estimate, and classify clients’ sentiments in terms of polarity, as expressed in public comments on social media (SM) company channels. The SAE is built on machine learning (ML) text classification models that are cross-source trained and validated with real data streams from a platform like Trustpilot that specializes in user reviews and tested on unseen comments gathered from a collection of public company pages and channels on a social networking platform like Facebook. Such crosssource opinion analysis remains a challenge and is highly relevant in the disciplines of research and engineering in which a sentiment classifier for an unlabeled destination domain is assisted by a tagged source task (Singh and Jaiswal, 2022). The best performance in terms of F1 score was obtained with a multinomial naive Bayes model: 0,87 for validation and 0,74 for testing.
Reputation has often been proposed as the central mechanism that creates trust in the sharing economy. However, some sharing platforms that focus primarily on social rather than economically driven exchanges have managed to facilitate exchanges between users without the use of a reputation system. This could indicate that socially driven exchanges are in less need of reputation systems and that having sufficient trust is less problematic. We examine the effect of seller reputation on sales and price as proxies for trust, using a large dataset from a Dutch meal-sharing platform. This platform aims to stimulate social interactions between people via meal sharing. Multilevel regression analyses were used to test the association of reputation with trust. Our main empirical results are that reputation affects both sales and price positively, consistent with the existing reputation literature. We also found evidence of the presence of an information effect, i.e., the influence of reputation on sharing decreases when additional profile information is provided (e.g., a profile photo, a product description). Our results thus confirm the effectiveness of reputation in more socially driven exchanges also. Consequently, platform owners are advised to use reputation on their platform to increase sharing between its users.
LINK
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%.
MULTIFILE
The project is a field study for several diverse hotel chains, including individual properties operated under the Marriott brand, Postillion Hotels. Each brand has unique values, missions, and visions. Therefore, this integration will lead to the development of company-specific sustainability strategies and processes. The study will use the model of levers of control to provide such tailor-made solutions and determine if a generic approach can be developed to match a corporate sustainability strategy with a corporate strategy and develop a supporting management control system for operationalizing the sustainability strategy. Research question: How can a hotel brand formulate and implement a sustainability strategy with a supporting management control system that not only complies with the new CSRD (Corporate Sustainability Reporting Directive) legislation but also emphasizes the creation of substantial value in financial and ESG (Environmental, Social, and Governance) aspects, based on double materiality, in line with the organization's corporate values and beliefs? Objective The aim is to develop a validated method, including tools, that hotels can use to create a sustainability strategy in line with the CSRD guidelines. This strategy should create value for the organization, the environment, and society, while aligning with the hotel's values and beliefs. Merely being compliant with the CSRD is not enough for hotels. Instead, they should view the implementation of the CSRD as an opportunity to stand out in terms of sustainability. By creating value in areas such as environment, safety, and governance, or through the six capitals (financial, manufactured, intellectual, human, social and relationship, and natural) that align with the UN-SDGs, and explicitly taking both an inside-out and an outside in perspective (double materiality), hotels can significantly enhance their sustainability reputation.
