scholarly journals Identifying Modes of User Engagement with Online News and Their Relationship to Information Gain in Text

Author(s):  
Nir Grinberg
2018 ◽  
Vol 168 (1) ◽  
pp. 31-47
Author(s):  
Michael Vaughan ◽  
Ariadne Vromen ◽  
Fiona Martin

Concerns about housing affordability in Australian capital cities have captured the public and political imagination. How, then, do ordinary citizens discuss the causes of and solutions to the increasing unaffordability of housing? This article examines evidence that branded Facebook channels provide a space for citizens to engage in everyday engagement and interaction on housing issues. We argue that studying branded, public Facebook pages, despite data access limitations, is an important way of tapping into broad citizen sentiment and understanding media influence on topical issues. We also find that different ways of framing housing affordability within news reporting are associated with different patterns of citizen engagement and interaction on Facebook. In particular, generational frames (critically linking housing affordability to either older people’s entrenched economic advantage or young people’s inability to save) are associated with high levels of user engagement, but the lowest level of discussion about policy solutions within dominant comment threads.


Author(s):  
M. Ali Fauzi ◽  
Agus Zainal Arifin ◽  
Sonny Christiano Gosaria

Since the rise of WWW, information available online is growing rapidly. One of the example is Indonesian online news. Therefore, automatic text classification became very important task for information filtering. One of the major issue in text classification is its high dimensionality of feature space. Most of the features are irrelevant, noisy, and redundant, which may decline the accuracy of the system. Hence, feature selection is needed. Maximal Marginal Relevance for Feature Selection (MMR-FS) has been proven to be a good feature selection for text with many redundant features, but it has high computational complexity. In this paper, we propose a two-phased feature selection method. In the first phase, to lower the complexity of MMR-FS we utilize Information Gain first to reduce features. This reduced feature will be selected using MMR-FS in the second phase. The experiment result showed that our new method can reach the best accuracy by 86%. This new method could lower the complexity of MMR-FS but still retain its accuracy.


2016 ◽  
Vol 68 (4) ◽  
pp. 869-883 ◽  
Author(s):  
Janette Lehmann ◽  
Carlos Castillo ◽  
Mounia Lalmas ◽  
Ricardo Baeza-Yates
Keyword(s):  

Author(s):  
Cecilie Givskov ◽  
Hans-Jörg Trenz

<p>Based on a pilot study of online news making and commenting in Denmark, the article discusses the relationship between online political news making and democracy. Empirical insights on the dynamics of user engagement and debates on mainstream Danish online news platforms are used to delineate the contours of the online public sphere. It is argued that the new digital media should be discussed not only as a new forum for political participation but also in relation to traditional forms of representative democracy. The analysis comprises the technical features and apps that are designed by online news providers in Denmark to facilitate the constitution of new “voice publics”. How these voice publics are designed as an element of news making and news distribution and, as such, linked to the old “representative” and “attentive publics” of news consumption is investigated.<strong></strong></p>


2014 ◽  
Vol 65 (10) ◽  
pp. 1988-2005 ◽  
Author(s):  
Ioannis Arapakis ◽  
Mounia Lalmas ◽  
B. Barla Cambazoglu ◽  
Mari-Carmen Marcos ◽  
Joemon M. Jose
Keyword(s):  

Author(s):  
Kevin Wise ◽  
Hyo Jung Kim ◽  
Jeesum Kim

A mixed-design experiment was conducted to explore differences between searching and surfing on cognitive and emotional responses to online news. Ninety-two participants read three unpleasant news stories from a website. Half of the participants acquired their stories by searching, meaning they had a previous information need in mind. The other half of the participants acquired their stories by surfing, with no previous information need in mind. Heart rate, skin conductance, and corrugator activation were collected as measures of resource allocation, motivational activation, and unpleasantness, respectively, while participants read each story. Self-report valence and recognition accuracy were also measured. Stories acquired by searching elicited greater heart rate acceleration, skin conductance level, and corrugator activation during reading. These stories were rated as more unpleasant, and their details were recognized more accurately than similar stories that were acquired by surfing. Implications of these results for understanding how people process online media are discussed.


Sign in / Sign up

Export Citation Format

Share Document