A comparison of methods for detecting hot topics

Abstract

In scientometrics for trend analysis, parameter choices for observing trends are often made ad hoc in past studies. For examples, different year spans might be used to create the time sequence and different indices were chosen for trend observation. However, the effectiveness of these choices was hardly known, quantitatively and comparatively. This work provides clues to better interpret the results when a certain choice was made. Specifically, by sorting research topics in decreasing order of interest predicted by a trend index and then by evaluating this ordering based on information retrieval measures, we compare a number of trend indices (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 (72500 papers vs. 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 index is robust under different conditions and is hardly affected even when the collection was split into arbitrary (e.g., only two) periods. Implications of these results are discussed. Our work does not only provide a method to evaluate trend prediction performance for scientometrics, but also provides insights and reflections for past and future trend observation studies.

A bibliometric investigation of research performance in emerging nanobiopharmaceuticals

“…Increasingly important research topics are of particular interest to those policy makers (Tseng, Lin, Lee, Hung, & Lee, 2009). In such situation, an attractive direction is to investigate the evolution footprints of an emerging research domain (Takeda et al, 2009), and detect hot topics (research fronts) of some important technological domains (e.g., Tseng et al, 2009). Research fronts represent the most dynamic areas of science and technology and the areas that attract the most scientific interest.…”

“…Scientometircs oriented to science mapping have seemly become most attractive for identifying research fronts and evolutions of some important scientific and technological domains, which is especially true for an emerging research domain (e.g., Small & Upham, 2009;Takeda et al, 2009;Tseng et al, 2009). In the remaining analysis, we employ visual co-word and co-citation network analyses to detect and map the intellectual structure as well as the evolution footprints of salient intellectual turning points in the nanobiopharmaceutical research.…”

Ontology Forecasting in Scientific Literature: Semantic Concepts Prediction Based on Innovation-Adoption Priors

“…The approaches for topic evolution can be distinguished in discriminative and generative [13]. The first ones consider topics as a distribution over words or a mixture over documents and analyse how these change in time using a variety of indexes and techniques [25]. For example, Morinaga and Yamanishi [19] employed a Finite Mixture Model to represent the structure of topics and analyse diachronically the extracted component and Mei and Zhai [16] correlated term clusters via a temporal graph model.…”

A novel approach to compute pattern history for trend analysis

“…There are previous studies of topic detection and trend analysis [4], [5], [6], [7]. In [4], Dan et al provided an interface called "FutureLens" for the user to explore frequently occurring terms or patterns in a collection of documents.…”