Understanding host marketing strategies on Airbnb and their impact on listing performance: a text analytics approach

PurposePeer-to-peer (P2P) accommodation sharing has become a significant part of the travel and lodging industry, allowing homeowners to engage in entrepreneurial activity via sharing of resources. However, there is limited understanding of how hosts can use listing descriptions to better match their offerings to different consumer segments. The purpose of this paper is to understand the use of listing descriptions by Airbnb hosts and the impact of such descriptions on sales performance.Design/methodology/approachIn this paper, a deep learning-based sentence-level aspect mining approach is used to extract various aspects from host-provided listing descriptions. Then a regression-based approach is used to understand the impact of various aspects of listing descriptions on listing performance.FindingsIt was found that aspects for which listing descriptions are the sole source of information have the greatest influence on listing performance. The authors also find that the impact of an aspect on listing performance varies by listing type, and that there is a mismatch between the most included aspects by hosts in their listing descriptions and the most influential aspects that impact sales.Originality/valueThe impact of consumer reviews in the context of Airbnb has been extensively studied. A novel aspect of this study is the exploration of P2P accommodations from a supplier perspective, by understanding the use and impact of host-provided textual descriptions on sales. The findings of this study can help better market properties from a practice perspective and better understand consumer information consumption from a theoretical perspective. The authors also demonstrate a new approach for exploring social phenomena by performing quantitative analysis on textual data using deep-learning and regression-based techniques.

Visual Analytics e Outlying Aspect Mining: contextualização de anomalias considerando questões temporais e multidimensionais

Outlying Aspect Mining (OAM) is a new way of handling outliers that, instead of focusing solely on the detection, also provides an explanation. This is done by presenting a subspace of attributes that had the most abnormal behavior. Acknowledging this group of attributes is important but only listing them is not sufficient for a human specialist to comprehend the situation and take the necessary actions. A higher-level, visual approach can improve the process, providing better cognitive clues to experts. Here we describe a Visual Analytics platform developed to present data and OAM outputs in a human-friendly interface. A novelty available on this platform is a parallel coordinates plot that also display temporal multidimensional data. Such representation overcome human visual system limitations and helps in the outlier investigation. To explore the applicability of the developed tool, a locomotive operation user case is employed with focus on fault analysis in an OAM point of view.

Hybrid Collaborative Fusion Based Product Recommendation Exploiting Sentiments from Implicit and Explicit Reviews

Product recommendation is an important functionality in online ecommerce systems. The goal of the recommendation system is to recommend products with has higher purchase success ratio. User profile, product purchase history etc. have been used in many works to provide high quality recommendations. Product reviews is one of the important source for personalized recommendation. Typical collaborative recommendation systems are built upon user rating on products. But in many cases, these rating information are inaccurate or not available. There is also a problem of biased reviews decreasing the accuracy of recommendation systems. This work proposes a aspect mining collaborative fusion based recommendation system considering both the implicit and explicit reviews. The sentiments about different aspects mined from reviews are translated to multi-dimensional ratings. These ratings are then fused with user profile and demographic attributes to improve the quality of recommendation. The proposed recommendation system has 3.79% lower RMSE, 4.51% lower MAE and 22% lower MRE compared to most recent collaborative filtering based recommendation system.

Foresight as a Tool for Managing the Socio-Economic Development of Mining Regions

At the present stage of development in the conditions of constant changes, the socio-economic development of mining areas is an extremely important issue for managers who make decisions, as the effectiveness of management tools depends on the further trajectory. In this aspect, mining regions need the introduction of modern management tools, taking into account the specifics of their functioning. However, the process of implementing such tools in practice can be a daunting task for the public management system. The article aims to explain the concept of using foresight technology in the management of socio-economic development of mining regions as a modern tool and to identify the main directions of its practical use. Based on the in-depth review of the scientific literature, a conceptual framework for improving the management of socio-economic development of mining regions in Ukraine is presented. It includes the gradual development of foresight-center of mining regions and foresightnetwork, which will improve public management of socio-economic development of mining regions.