BizSeeker: A hybrid semantic recommendation system for personalized government‐to‐business e‐services

The purpose of this paper is to develop a hybrid semantic recommendation system to provide personalized government to business (G2B) e‐services, in particular, business partner recommendation e‐services for Australian small to medium enterprises (SMEs).

The study first proposes a product semantic relevance model. It then develops a hybrid semantic recommendation approach which combines item‐based collaborative filtering (CF) similarity and item‐based semantic similarity techniques. This hybrid approach is implemented into an intelligent business‐partner‐locator recommendation‐system prototype called BizSeeker.

The hybrid semantic recommendation approach can help overcome the limitations of existing recommendation techniques. The recommendation system prototype, BizSeeker, can recommend relevant business partners to individual business users (e.g. exporters), which therefore will reduce the time, cost and risk of businesses involved in entering local and international markets.

The study would be of great value in e‐government personalization research. It would facilitate the transformation of the current G2B e‐services into a new stage wherein the e‐government agencies offer personalized e‐services to business users. The study would help government policy decision‐makers to increase the adoption of e‐government services.

Providing personalized e‐services by e‐government can be seen as an evolution of the intentions‐based approach and will be one of the next directions of government e‐services. This paper develops a new recommender approach and systems to improve personalization of government e‐services.