nep-ict New Economics Papers
on Information and Communication Technologies
Issue of 2010‒06‒18
two papers chosen by
Walter Frisch
University Vienna

  1. Twitter Adoption in Congress: Who Tweets First? By Chi, Feng; Yang, Nathan
  2. Learning Machines Supporting Bankruptcy Prediction By Wolfgang Karl Härdle; Rouslan Moro; Linda Hoffmann

  1. By: Chi, Feng; Yang, Nathan
    Abstract: Our general objective is to characterize the recent and well publicized diffusion of Twitter among politicians in the United States 111th House of Representatives. Ultimately, Barrack Obama, Facebook and peers matter when it comes to the propensity and speed of Twitter adoption. A basic analysis of the distribution of first Tweets over time reveals clustering around the President's inauguration; which holds regardless whether the adopter is Democratic or Republican, or an incumbent or newcomer. After we characterize which representatives are most likely to adopt Twitter, we confirm the widespread belief that Facebook and Twitter are indeed complementary technology. Given their perceived desire for accessible government, a surprising result is that Republicans are more likely to adopt Twitter than Democrats. Finally, using the exact dates of each adopter's first Tweet, we demonstrate that the diffusion of Twitter is faster for those representatives with a larger number of peers already using the technology, where peers are defined by two social networks: (1) Politicians representing the same state; and (2) politicians belonging to the same committees; especially so for those in committee networks. This observed behavior can be rationalized by social learning, as the instances in which the peer effects are important correspond to the cases in which social learning is relevant.
    Keywords: Communication; diffusion of technology; political marketing; social interaction; social media; social learning.
    JEL: M3 D83 D85
    Date: 2010–06–09
  2. By: Wolfgang Karl Härdle; Rouslan Moro; Linda Hoffmann
    Abstract: In many economic applications it is desirable to make future predictions about the financial status of a company. The focus of predictions is mainly if a company will default or not. A support vector machine (SVM) is one learning method which uses historical data to establish a classification rule called a score or an SVM. Companies with scores above zero belong to one group and the rest to another group. Estimation of the probability of default (PD) values can be calculated from the scores provided by an SVM. The transformation used in this paper is a combination of weighting ranks and of smoothing the results using the PAV algorithm. The conversion is then monotone. This discussion paper is based on the Creditreform database from 1997 to 2002. The indicator variables were converted to financial ratios; it transpired out that eight of the 25 were useful for the training of the SVM. The results showed that those ratios belong to activity, profitability, liquidity and leverage. Finally, we conclude that SVMs are capable of extracting the necessary information from financial balance sheets and then to predict the future solvency or insolvent of a company. Banks in particular will benefit from these results by allowing them to be more aware of their risk when lending money.
    Keywords: Support Vector Machine, Bankruptcy, Default Probabilities Prediction, Profitability
    JEL: C14 G33 C45
    Date: 2010–06

This nep-ict issue is ©2010 by Walter Frisch. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.