Analysis of Factors that affect Users’ Behavioral Changes in News Service

A variety of information is transmitted through websites, which often requires users to give immediate and appropriate reactions. Consequently, users must make ever greater efforts to select information themselves, and this is fueling further improvements in recommendation services that can reduce such burdens. On the other hand, filter bubbles that only provide biased information to users are generated due to redundant recommendations. Previous research has analyzed the behavioral changes of users on existing news sites, and findings have suggested that the index of diversity of browsed articles decreases over time. However, no consideration has been given to the change in the category diversity of articles across news media and the influence of the number of views. In this research, we propose a method to evaluate the relationship between the change in diversity and the period and number of views by dividing the target period at regular intervals and evaluating the diversity of article categories by considering the readability of each article based on the number of views. Then, we analyze the relationship between the change in diversity of the entire media and the change in the variety of articles viewed by users on the actual online media, as well as the influence of the period and number of views on the change in diversity. As a result, there is a correlation between changes in user behavior and changes in the number of browsing times. Furthermore, the results indicate that the change in the category diversity of articles across news media has a strong impact on the change in the diversity of users.

[1]  A. Azzouz.  2011 , 2020, City.

[2]  A.M.J. Derks.  Post-broadcast democracy: How media choice increases inequality in political involvement and polarizes elections , 2009 .

[3]  Eli Pariser,et al.  The Filter Bubble: What the Internet Is Hiding from You , 2011 .

[4]  Dietmar Jannach,et al.  What recommenders recommend: an analysis of recommendation biases and possible countermeasures , 2015, User Modeling and User-Adapted Interaction.

[5]  Daniel M. Butler,et al.  The World Wide Web and the U.S. Political News Market , 2010 .

[6]  Fujio Toriumi,et al.  Analysis and Modeling of Behavioral Changes in a News Service , 2018, 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI).

[7]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

[8]  David M. Pennock,et al.  Categories and Subject Descriptors , 2001 .

[9]  A. M. Madni,et al.  Recommender systems in e-commerce , 2014, 2014 World Automation Congress (WAC).

[10]  Eli Pariser.  FILTER BUBBLE: Wie wir im Internet entmündigt werden , 2012 .

[11]  Ichiro Fukuda,et al.  What Influences People to Broaden Their Horizons? , 2018, 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI).

[12]  S. Sénécal,et al.  The influence of online product recommendations on consumers' online choices , 2004 .

[13]  Kartik Hosanagar,et al.  Blockbuster Culture's Next Rise or Fall: The Impact of Recommender Systems on Sales Diversity , 2007, Manag. Sci..

[14]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[15]  Loren G. Terveen,et al.  Exploring the filter bubble: the effect of using recommender systems on content diversity , 2014, WWW.

[16]  Lada A. Adamic,et al.  Exposure to ideologically diverse news and opinion on Facebook , 2015, Science.