Using a two-stage technique to design a keyword suggestion system

Introduction. The study of keyword suggestion in the field of search engine marketing is an important issue for paid search advertising or sponsored advertisements. The challenge of this issue is not only to suggest the relevant keywords, but also to find more such keywords. Methods. In this paper, we propose a system, the main goal of which is not only to suggest a list of relevant keywords, but also to determine the degree of similarity between the user's query and each suggested keyword. Analysis. Three experiments were performed to illustrated the performance comparison between different systems and the relevant parameters considered in our system. Results. According to the results of the first experiment, our system was found to be better than other online systems. According to the results of the second experiment, we concluded that the performance model. According to the results of the third experiment, we verified that the termination criteria of our system could yield a cost effective solution within a controlled period of time. Conclusions. In this paper, we make several contributions. First, we propose an intelligent system that is based on several semantic analysis methods, Second, we define a new performance metric to compare the results of different systems. Third, we design a combined technique to find a cost effective solution with controlled period of time.