%0 Conference Paper %1 yan2011citation %A Yan, Rui %A Tang, Jie %A Liu, Xiaobing %A Shan, Dongdong %A Li, Xiaoming %B Proceedings of the 20th ACM international conference on Information and knowledge management %C New York, NY, USA %D 2011 %I ACM %K citation prediction scientometrics %P 1247--1252 %R 10.1145/2063576.2063757 %T Citation count prediction: learning to estimate future citations for literature %U http://doi.acm.org/10.1145/2063576.2063757 %X In most of the cases, scientists depend on previous literature which is relevant to their research fields for developing new ideas. However, it is not wise, nor possible, to track all existed publications because the volume of literature collection grows extremely fast. Therefore, researchers generally follow, or cite merely a small proportion of publications which they are interested in. For such a large collection, it is rather interesting to forecast which kind of literature is more likely to attract scientists' response. In this paper, we use the citations as a measurement for the popularity among researchers and study the interesting problem of Citation Count Prediction (CCP) to examine the characteristics for popularity. Estimation of possible popularity is of great significance and is quite challenging. We have utilized several features of fundamental characteristics for those papers that are highly cited and have predicted the popularity degree of each literature in the future. We have implemented a system which takes a series of features of a particular publication as input and produces as output the estimated citation counts of that article after a given time period. We consider several regression models to formulate the learning process and evaluate their performance based on the coefficient of determination (R-square). Experimental results on a real-large data set show that the best predictive model achieves a mean average predictive performance of 0.740 measured in R-square, which significantly outperforms several alternative algorithms. %@ 978-1-4503-0717-8

@inproceedings{yan2011citation, abstract = {In most of the cases, scientists depend on previous literature which is relevant to their research fields for developing new ideas. However, it is not wise, nor possible, to track all existed publications because the volume of literature collection grows extremely fast. Therefore, researchers generally follow, or cite merely a small proportion of publications which they are interested in. For such a large collection, it is rather interesting to forecast which kind of literature is more likely to attract scientists' response. In this paper, we use the citations as a measurement for the popularity among researchers and study the interesting problem of Citation Count Prediction (CCP) to examine the characteristics for popularity. Estimation of possible popularity is of great significance and is quite challenging. We have utilized several features of fundamental characteristics for those papers that are highly cited and have predicted the popularity degree of each literature in the future. We have implemented a system which takes a series of features of a particular publication as input and produces as output the estimated citation counts of that article after a given time period. We consider several regression models to formulate the learning process and evaluate their performance based on the coefficient of determination (R-square). Experimental results on a real-large data set show that the best predictive model achieves a mean average predictive performance of 0.740 measured in R-square, which significantly outperforms several alternative algorithms.}, acmid = {2063757}, added-at = {2012-03-15T10:04:27.000+0100}, address = {New York, NY, USA}, author = {Yan, Rui and Tang, Jie and Liu, Xiaobing and Shan, Dongdong and Li, Xiaoming}, biburl = {https://www.bibsonomy.org/bibtex/2b0caabb6e17d9b790d3f13c897330aad/sdo}, booktitle = {Proceedings of the 20th ACM international conference on Information and knowledge management}, description = {Citation count prediction}, doi = {10.1145/2063576.2063757}, interhash = {71ec0933a36df3dd21f38285bdf9b1b0}, intrahash = {b0caabb6e17d9b790d3f13c897330aad}, isbn = {978-1-4503-0717-8}, keywords = {citation prediction scientometrics}, location = {Glasgow, Scotland, UK}, numpages = {6}, pages = {1247--1252}, publisher = {ACM}, series = {CIKM '11}, timestamp = {2012-03-15T10:04:27.000+0100}, title = {Citation count prediction: learning to estimate future citations for literature}, url = {http://doi.acm.org/10.1145/2063576.2063757}, year = 2011 }