Acceso abierto

Differences between journal and conference in computer science: a bibliometric view based on Bayesian network

,  y   
25 ago 2023

Cite
Descargar portada

Algorithm 1:

amended K2 algorithm
amended K2 algorithm

Figure 1.

The learned Bayesian network.
The learned Bayesian network.

Figure 2.

An example of Bayesian network inference by setting Category as journal.
An example of Bayesian network inference by setting Category as journal.

Figure 3.

The distribution of Category by setting various HIM and pNumM and auCDM.
The distribution of Category by setting various HIM and pNumM and auCDM.

Figure 4.

The distribution of Category by setting pNumM=(FiftyHundred, gtHundred), HIM=(FiftyHundred, gtHundred), auCDM=(mhigh,high).
The distribution of Category by setting pNumM=(FiftyHundred, gtHundred), HIM=(FiftyHundred, gtHundred), auCDM=(mhigh,high).

Figure 5.

mhigh or above CNCI probability by setting various Category and Rank.
mhigh or above CNCI probability by setting various Category and Rank.

Figure 6.

Distribution of refNum/abLen by setting various Category.
Distribution of refNum/abLen by setting various Category.

Figure 7.

mhigh or above pNov/pDisrupt probability by setting various Category.
mhigh or above pNov/pDisrupt probability by setting various Category.

Figure 8.

mhigh or above pNov/pDisrupt probability by setting various Category and Rank.
mhigh or above pNov/pDisrupt probability by setting various Category and Rank.

Discretization rules of factors (Sun et al_, 2023)_

Variable Discretization rule
pNov 0: zero; [0, 0.4]: low; (0.4, 0.6]; median; (0.6, 0.8]: mhigh; (0.8, 1]: high
pDisrupt <0: ngtzero; sort pDisrupt values and divide by top percentage interval: (70%, 100%]: low; (30%, 70%]: medium; (10%, 30%]: mhigh; (0%, 10%]: high
refNum [0, 10]: ltTen; (10, 20]: tenTwenty; (20, 30]: twentyThirty; > 30: gtThirty
abRE >70: easy; (50, 70]: medium; (40, 50]: mhard; (30, 40]: hard; <30: vhard (ref. Flesch, 1948)
abLen <600: short; (600, 800]; median; (800, 1000]: long; >1000: vlong
pNumF [0, 10]: ltTen; (10, 20]: tenTwenty; (20, 50]: twentyFifty; (50, 100]: FiftyHundred; > 100:
pNumM gtHundred
tcF [0, 10]: ltTen; (10, 100]: tenHundred; (100, 500]: HundredFiveH; (500, 2000]: fiveHTwentyH;
tcM (2000, 10000]: twentyHHundredH; > 10000: gtHundredH
HIF [0, 10]: ltTen; (10, 20]: tenTwenty; (20, 30]: twentyThirty; (30, 50]: thirtyFifty; (50, 100]:
HIM FiftyHundred
auCDFauCDMinstCDFinstCDM sort auCDF/auCDM values and divide by top percentage interval: (50%, 100%]: low; (20%, 50%]: mlow; (10%, 20%]: medium; (5%, 10%]: mhigh; (0%, 5%]: high
auNuminstNum 1: one; 2: tow; 3: three; 4: four; 5: five; >5: gtfive
CNCI (0, 0.3]: low; [0.3, 0.8]: mlow; (0.8, 1.2]; average; (1.2, 2]: mhigh; (2, 5]: vhigh; >5: exhigh
Idioma:
Inglés
Calendario de la edición:
4 veces al año
Temas de la revista:
Informática, Tecnologías de la información, Gestión de proyectos, Bases de datos y minería de datos