Chronological citation recommendation with time preference

Citation recommendation is an important task to assist scholars in finding candidate literature cite. Traditional studies focus on static models of recommending citations, which do not explicitly distinguish differences between papers that are caused by temporal variations. Although, some researchers have investigated chronological citation adding time related function or modeling textual topics dynamically. These solutions can hardly cope with generalization cold-start problems when there no information for user profiling isolated never being cited. With the rise and fall science paradigms, scientific tend change evolve over time. People would preference citing papers, since most theoretical basis exist classical readings published old time, while new techniques proposed more recent papers. To explore recommendation, this paper wants predict based queries, a probability distribution different slices. Then, we use re-rank initial list obtained content-based filtering. Experimental results demonstrate performance be further enhanced it’s flexible added other frameworks.