The Mark 5 System of Automatic Coding for TREAC

Author(s):  
T. PEARCEY ◽  
S.N. HIGGINS ◽  
P.M. WOODWARD
Keyword(s):  
Author(s):  
Leili Tavabi ◽  
Kalin Stefanov ◽  
Larry Zhang ◽  
Brian Borsari ◽  
Joshua D. Woolley ◽  
...  

1960 ◽  
Vol 1 ◽  
pp. 23-31
Author(s):  
T Pearcey ◽  
S.N Higgins ◽  
P.M Woodward
Keyword(s):  

1993 ◽  
Vol 18 (1) ◽  
pp. 53-59 ◽  
Author(s):  
C. R. Rossi ◽  
V. Alberti ◽  
G. Mancino ◽  
L. Flor ◽  
T. Martello ◽  
...  

1993 ◽  
Vol 77 (1) ◽  
pp. 259-269 ◽  
Author(s):  
Paola Marangolo ◽  
Enrico Di Pace ◽  
Luigi Pizzamiglio

Two experiments were run to test whether the automatic coding of colors generates priming effects. Subjects were tachistoscopically presented a series of prime-target sequences. The prime stimulus could be either a red, green, or black circular dot, followed by a red or green annular ring (target). The role of automatic and conscious mechanisms was investigated in Exp. 1 by manipulating the predictive validity of the prime stimuli (80%, 50%, 20%), keeping constant the value of stimulus-onset asynchrony (350 msec.). Analysis showed priming effects even in the low predictive condition, where no conscious expectations could be activated. In Exp. 2, three different values of stimulus-onset asynchrony were used, 150, 350, and 2100 msec. Priming effects were obtained in the short and medium stimulus-onset asynchrony condition but not in the long one. Over-all, the data of both experiments produce converging evidence which indicates that the automatic elaboration of colored stimuli may produce priming effects.


Author(s):  
Bjorn Burscher ◽  
Rens Vliegenthart ◽  
Claes H. De Vreese

Content analysis of political communication usually covers large amounts of material and makes the study of dynamics in issue salience a costly enterprise. In this article, we present a supervised machine learning approach for the automatic coding of policy issues, which we apply to news articles and parliamentary questions. Comparing computer-based annotations with human annotations shows that our method approaches the performance of human coders. Furthermore, we investigate the capability of an automatic coding tool, which is based on supervised machine learning, to generalize across contexts. We conclude by highlighting implications for methodological advances and empirical theory testing.


Sign in / Sign up

Export Citation Format

Share Document