Front-page news selection is the task of finding important news articles in news aggregators. In this study, we examine news selection for public front pages using raw text, without any meta-attributes such as click counts. A novel algorithm is introduced by jointly considering the importance and diversity of selected news articles and the length of front pages. We estimate the importance of news, based on topic modelling, to provide the required diversity. Then we select important documents from important topics using a priority-based method that helps in fitting news content into the length of the front page. A user study is subsequently conducted to measure effectiveness and diversity, using our newly-generated annotation program. Annotation results show that up to seven of 10 news articles are important and up to nine of them are from different topics. Challenges in selecting public front-page news are addressed with an emphasis on future research.
EildersC. The role of news factors in media use. Discussion Papers, Research Unit, The Public and the Social Movement. Social Science Research Center Berlin (WZB), 1996, pp. 96–104.
2.
GaltungJRugeMH. The structure of foreign news. Journal of Peace Research1965; 2: 64–91.
3.
LiuJDolanPPedersenER. Personalized news recommendation based on click behavior. In: Proceedings of the 15th ınternational conference on ıntelligent user ınterfaces, Hong Kong. New York: ACM, 2010, pp. 31–40.
4.
BleiDM. Probabilistic topic models. Communications of the ACM2012; 55: 77–84.
ZubiagaA. Newspaper editors vs the crowd: On the appropriateness of front-page news selection. In: WWW companion volume. International World Wide Web Conferences Steering Committee/ACM, 2013, pp. 879–880.
7.
HerlockerJLKonstanJATerveenLGRiedlJT. Evaluating collaborative filtering recommender systems. ACM Transactions of Information Systems2004; 22: 5–53.
8.
AhnJ-wBrusilovskyPGradyJHeDSynSY. Open user profiles for adaptive news systems: help or harm? In: Proceedings of the 16th ınternational conference on World Wide Web, Banff, Canada. New York: ACM, 2007, pp. 11–20.
9.
BillsusDPazzaniMJ. A hybrid user model for news story classification. In: Proceedings of the seventh ınternational conference on user modeling, Banff, Canada. New York: Springer, 1999, pp. 99–108.
10.
GoodNSchaferJBKonstanJA. Combining collaborative filtering with personal agents for better recommendations. In: Proceedings of the sixteenth national conference on artificial ıntelligence and the eleventh ınnovative applications of artificial ıntelligence conference ınnovative applications of artificial ıntelligence, Orlando, FL. American Association for Artificial Intelligence, 1999, pp. 439–446.
11.
DasASDatarMGargARajaramS. Google news personalization: scalable online collaborative filtering. In: Proceedings of the 16th international conference on World Wide Web, Banff, Canada. New York: ACM, 2007, pp. 271–280.
12.
ChuWParkS-T. Personalized recommendation on dynamic content using predictive bilinear models. In: Proceedings of the 18th ınternational conference on World Wide Web, Madrid. New York: ACM, 2009, pp. 691–700.
13.
CarbonellJGoldsteinJ. The use of MMR, diversity-based reranking for reordering documents and producing summaries. In: Proceedings of the 21st annual ınternational ACM SIGIR conference on research and development in ınformation retrieval, Melbourne. New York: ACM, 1998, pp. 335–336.
14.
ClarkeCLAKollaMCormackGV. Novelty and diversity in information retrieval evaluation. In: Proceedings of the 31st annual ınternational ACM SIGIR conference on research and development in ınformation retrieval, Singapore. New York: ACM, 2008, pp. 659–666.
ZieglerC-NMcNeeSMKonstanJALausenG. Improving recommendation lists through topic diversification. In: Proceedings of the 14th ınternational conference on World Wide Web, Chiba, Japan. New York: ACM, 2005, pp. 22–32.
17.
NewmanM. Power laws, Pareto distributions and Zipf’s law. Contemporary Physics2005; 46: 323–351.
18.
ClausetAShaliziCRNewmanMEJ. Power-law distributions in empirical data. SIAM Reviews2009; 51: 661–703.
19.
TehYWJordanMIBealMJBleiDM. Hierarchical Dirichlet processes. Journal of the American Statistical Association2006; 101: 1566–1581.
ToramanCCanFKocberberS. Developing a text categorization template for Turkish news portals. In: 2011 International symposium on ınnovations in ıntelligent systems and applications (INISTA), 2011, pp. 379–383.
24.
CanFKocberberSBalcikEKaynakCOcalanHCVursavasOM. Information retrieval on Turkish texts. Journal of the American Society for Information Science and Technology2008; 59: 407–421.
25.
McCallumAK. MALLET: Machine learning for language toolkit, http://mallet.cs.umass.edu (2015, accessed 5 May 2015).
26.
FleissJL. Measuring nominal scale agreement among many raters. Psychological Bulletin1971; 76: 378–382.
27.
LandisJRKochGG. The measurement of observer agreement for categorical data. Biometrics1977; 33: 159–174.
