Filters








63,344 Hits in 5.3 sec

Toward the attribution of Web behavior

Myriam Abramson
2012 2012 IEEE Symposium on Computational Intelligence for Security and Defence Applications  
Furthermore, just like keystroke authentication, attribution of Web behavior is not obtrusive and has applications in cyberwarfare as a new biometric technique.  ...  identifying an individual within a set of individuals.  ...  After training, the prediction and evaluation of the most likely sequence for each user can be made by following the optimal policy mapping states to actions learned for this user with Eq. 4 where g i  ... 
doi:10.1109/cisda.2012.6291524 dblp:conf/cisda/Abramson12 fatcat:7zxkjpblnnaspivwpxqcqhogtu

Modeling and Understanding Human Routine Behavior

Nikola Banovic, Tofi Buzali, Fanny Chevalier, Jennifer Mankoff, Anind K. Dey
2016 Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems - CHI '16  
used in our work, and Julian Ramos and Christine Bauer for discussions about human routine behavior.  ...  The authors would like to thank Brian Ziebart for his valuable input regarding the MaxCasualEnt algorithm, Scott Davidoff and Jin-Hyuk Hong for their help in obtaining and understanding the two datasets  ...  Quantifying Routineness of Human Behavior Although we are not interested in the predictive power of the MaxCausalEnt IRL per se, we use the task of predicting the next action given a state to evaluate  ... 
doi:10.1145/2858036.2858557 dblp:conf/chi/BanovicBCMD16 fatcat:nwp37ks4hfhb7efklupnazjlpm

Computational Social Scientist Beware: Simpson's Paradox in Behavioral Data [article]

Kristina Lerman
2017 arXiv   pre-print
I illustrate Simpson's paradox with several examples coming from studies of online behavior and show that aggregate response leads to wrong conclusions about the underlying individual behavior.  ...  Heterogeneity predisposes analysis to Simpson's paradox, whereby the trends observed in data that has been aggregated over the entire population may be substantially different from those of the underlying  ...  In this case, the trends discovered in disaggregated data are more likely to describe-and predict-individual behavior than the trends found in aggregate data.  ... 
arXiv:1710.08615v1 fatcat:ap47dtv7sbbdhls7vbb7kcv6oe

Behavior-based web page evaluation

Ganesan Velayathan, Seiji Yamada
2006 Proceedings of the 15th international conference on World Wide Web - WWW '06  
We successfully confirmed, for example, that time spent on a Web page is not the most important factor in predicting interest from behavior, which conflicts with the findings of most previous studies.  ...  This paper describes our efforts to investigate factors in user browsing behavior to automatically evaluate Web pages that the user shows interest in.  ...  user interest.  ... 
doi:10.1145/1135777.1135905 dblp:conf/www/VelayathanY06 fatcat:pq6cfcjr4fbfdki6blo5ppluyu

Behavior based web page evaluation

Ganesan Velayathan, Seiji Yamada
2007 Proceedings of the 16th international conference on World Wide Web - WWW '07  
We successfully confirmed, for example, that time spent on a Web page is not the most important factor in predicting interest from behavior, which conflicts with the findings of most previous studies.  ...  This paper describes our efforts to investigate factors in user browsing behavior to automatically evaluate Web pages that the user shows interest in.  ...  user interest.  ... 
doi:10.1145/1242572.1242828 dblp:conf/www/VelayathanY07 fatcat:mwjr6dv6fbdsbnmi42zkwvbwhe

Behavior-Based Web Page Evaluation

Ganesan Velayathan, Seiji Yamada
2006 2006 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology Workshops  
We successfully confirmed, for example, that time spent on a Web page is not the most important factor in predicting interest from behavior, which conflicts with the findings of most previous studies.  ...  This paper describes our efforts to investigate factors in user browsing behavior to automatically evaluate Web pages that the user shows interest in.  ...  user interest.  ... 
doi:10.1109/wi-iatw.2006.51 dblp:conf/iat/VelayathanY06 fatcat:nndnzitrafdlbklmv4avhwjnea

Computational social scientist beware: Simpson's paradox in behavioral data

Kristina Lerman
2017 Journal of Computational Social Science  
I illustrate Simpson's paradox with several examples coming from studies of online behavior and show that aggregate response leads to wrong conclusions about the underlying individual behavior.  ...  Heterogeneity predisposes analysis to Simpson's paradox, whereby the trends observed in data that have been aggregated over the entire population may be substantially different from those of the underlying  ...  In this case, the trends discovered in disaggregated data are more likely to describe-and predict-individual behavior than the trends found in aggregate data.  ... 
doi:10.1007/s42001-017-0007-4 fatcat:g62dxxz4cjhfrnh7s2nw7hoxaa

Personalized Behavior Recommendation

Steven Tang, Zachary A. Pardos
2017 Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization - UMAP '17  
We stipulate that this approach touches on factors more aligned with personalization, since the prediction of behavior is an aggregation of the student's cognitive abilities, affective state, and preferences  ...  This framework trained a behavior model on millions of previous student actions in order to estimate how a future learner might behave.  ...  By allowing a learner to jump to the page they are predicted to spend the most time on next, time spent by the user searching for the relevant page could be saved.  ... 
doi:10.1145/3099023.3099038 dblp:conf/um/TangP17 fatcat:idmfa2vvgfez5pz7dvr65gooc4

Characterizing and Predicting Enterprise Email Reply Behavior

Liu Yang, Susan T. Dumais, Paul N. Bennett, Ahmed Hassan Awadallah
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
Most previous research on email is based on either relatively small data samples from user surveys and interviews, or on consumer email accounts such as those from Yahoo! Mail or Gmail.  ...  We also analyze the importance of different features on reply behavior predictions.  ...  For reply action, it predicts 0 (no reply) if there is no previous reply behavior from {u j } to u i .  ... 
doi:10.1145/3077136.3080782 dblp:conf/sigir/0019DBA17 fatcat:pijsz57xjffbbmwpuhw62cvyl4

Predicting Individual Behavior with Social Networks

Sharad Goel, Daniel G. Goldstein
2014 Marketing science (Providence, R.I.)  
Across all domains, we find that social data are informative in identifying individuals who are most likely to undertake various actions, and moreover, such data improve on both demographic and behavioral  ...  Although the similarity of connected individuals is well established, it is unclear whether behavioral predictions based on social data are more accurate than those arising from current marketing practices  ...  In many contexts, the central objective is to identify pools of individuals most likely to take action.  ... 
doi:10.1287/mksc.2013.0817 fatcat:kz2k6a5jgjdobatnskkwcifbru

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation [article]

Chang Zhou, Jinze Bai, Junshuai Song, Xiaofei Liu, Zhengchao Zhao, Xiusi Chen, Jun Gao
2017 arXiv   pre-print
We further explore ATRank to use one unified model to predict different types of user behaviors at the same time, showing a comparable performance with the highly optimized individual models.  ...  When a downstream application requires to facilitate the modeled user features, it may lose the integrity of the specific highly correlated behavior of the user, and introduce noises derived from unrelated  ...  Besides, the aggregated features also lose information of any individual behavior that could be precisely related with the object that needs to be predicted in the downstream application.  ... 
arXiv:1711.06632v2 fatcat:2gkxhdgrczcdhimcldz4d5el2u

User Behavior and Change

Arnau Gavaldà-Miralles, John S. Otto, Fabián E. Bustamante, Luís A.N. Amaral, Jordi Duch, Roger Guimerà
2014 Proceedings of the 10th ACM International on Conference on emerging Networking Experiments and Technologies - CoNEXT '14  
In this paper, we introduce an approach to model user behavior based on a hidden Markov model and apply it to analyze a twoyear-long user-level trace of download activity of over 38k users from around  ...  This approach allows us to quantify the true impact of file-sharing laws on user behavior, identifying behavioral trends otherwise difficult to identify.  ...  We apply this approach to detect the impact of copyright infringement legislation and legal action on user behavior.  ... 
doi:10.1145/2674005.2675009 dblp:conf/conext/Gavalda-MirallesOBADG14 fatcat:pefsxxn5uvhbzjrymqqb6ldvge

Modeling decision points in user search behavior

Paul Thomas, Alistair Moffat, Peter Bailey, Falk Scholer
2014 Proceedings of the 5th Information Interaction in Context Symposium on - IIiX '14  
Understanding and modeling user behavior is critical to designing search systems: it allows us to drive batch evaluations, predict how users would respond to changes in systems or interfaces, and suggest  ...  We propose an experiment to test this, and to elucidate other factors which influence user actions.  ...  of the "decide next action" decision point.  ... 
doi:10.1145/2637002.2637032 dblp:conf/iiix/ThomasMBS14 fatcat:m4i3m6amx5gihpmrdmp5gok5qy

Using cross-game behavioral markers for early identification of high-risk internet gamblers

Julia Braverman, Debi A. LaPlante, Sarah E. Nelson, Howard J. Shaffer
2013 Psychology of Addictive Behaviors  
The Cambridge Health Alliance, a Harvard Medical School Teaching Affiliate Using actual gambling behavior provides the opportunity to develop behavioral markers that operators can use to predict the development  ...  Using the daily aggregated Internet betting transactions for gamblers' first 31 calendar days of online betting activities at bwin.party, we employed a 2-step analytic strategy: (a) applying an exploratory  ...  and predicting RG membership from two games/live action variability) and the combined model (i.e., predicting RG membership from either set of variables).  ... 
doi:10.1037/a0032818 pmid:24059836 fatcat:qq4i57ginrctjah3sit7qz7ca4

FACTORS INFLUENCING ONLINE VIOLENT BEHAVIORS AND APPROACHES TO EFFECT ONLINE VIOLENT BEHAVIORS

Yi Zhong, Mengyu Xiao
2021 Cultural Communication and Socialization Journal  
of Internet users.  ...  Based on previous studies, this study selected two independent variables, social media experience and community behavior, from two aspects of environment and behavior respectively, and analyzed with online  ...  The followup research can be carried out from the following aspects.  ... 
doi:10.26480/ccsj.02.2021.75.80 fatcat:36se43c72rfmlbr77iq6yl3isa
« Previous Showing results 1 — 15 out of 63,344 results