No abstract

Besides the typical applications of recommender systems in B2C scenarios such as movie or shopping platforms, there is a rising interest in transforming the human-driven advice provided, e.g., in consultancy via the use of recommender systems. We explore the special characteristics of such knowledge-based B2B services and propose a process that allows incorporating recommender systems into them. We suggest and compare several recommender techniques that allow incorporating the necessary contextual knowledge (e.g., company demographics). These techniques are evaluated in isolation on a test set of business intelligence consultancy cases. We then identify the respective strengths of the different techniques and propose a new hybridisation strategy to combine these strengths. Our results show that the hybridisation leads to substantial performance improvement over the individual methods.

We conduct a computational analysis of the literature on Conversational AI. We identify the trend based on all publications until the year 2020. We then concentrate on the publications for the last five years between 2016 and 2020 to find out the top ten venues and top three journals where research on Conversational AI has been published. Further, using the Latent Dirichlet Allocation (LDA) topic modeling technique, we discover nine important topics discussed in Conversational AI literature and specifically two topics related to the area of coaching. Finally, we detect the key authors who have contributed significantly to Conversational AI research and area(s) related to coaching. We determine the key authors' areas of expertise and how the knowledge is distributed across different regions. Our findings show an increasing trend and thus, an interest in Conversational AI research, predominantly from the authors in Europe.

No abstract

Besides the typical applications of recommender systems in B2C scenarios such as movie or shopping platforms, there is a rising interest in transforming the human-driven advice provided e.g. in consultancy via the use of recommender systems. We explore the special characteristics of such knowledge-based B2B services and propose a process that allows to incorporate recommender systems into them. We suggest and compare several recommender techniques that allow to incorporate the necessary contextual knowledge (e.g. company demographics). These techniques are evaluated in isolation on a test set of business intelligence consultancy cases. We then identify the respective strengths of the different techniques and propose a new hybridisation strategy to combine these strengths. Our results show that the hybridisation leads to a substantial performance improvement over the individual methods.