Please use this identifier to cite or link to this item:
|Title:||Which Kinds of Trend Metrics Are More Effective for Emerging Trend Detection?|
Hung, Wen-Chi;Lee, Yi-Yang
;Trend metrics;Eigen-trend;Linear regression;Evaluation;Information retrieval
|Issue Date:||2016-06-24 17:10:27 (UTC+8)|
In scientometrics for trend analysis, parameter choices for observing trends are often made ad hoc in past studies. However, the effectiveness of these choices was hardly examined, quantitatively and comparatively. This work provides clues to better interpret the results when a certain parameter choice is made. Specifically, by sorting research topics in descending order of interest predicted by a trend metric and then by evaluating this ordering based on information retrieval measures, we compare a number of trend metrics (percentage of increase vs. regression slope), trend formulations (simple trend vs. eigen-trend), and options (various year spans and durations for prediction) in different domains (safety agriculture and information retrieval) with different collection scales (72,500 papers and 853 papers) to know which one leads to better trend observation. Our results show that the slope of linear regression on the time series performs constantly better than the others. More interestingly, this metric is robust under different conditions and is hardly affected even when the collection is split into arbitrary periods. Implications of these results are discussed. Our work not only provides a method to evaluate trend prediction performance for scientometrics, but also offers insights and reflections for past and future trend observation studies.
|Relation:||圖書與資訊學刊, 68(1:1), 12-29|
Journal of Librarianship and Information Science
|Appears in Collections:||[Journal of Librarianship and Information Science] Journal Articles|
Files in This Item:
All items in 學術集成 are protected by copyright, with all rights reserved.