Filters








280,049 Hits in 6.9 sec

Predicting Human Activities from User-Generated Content

Steven Wilson, Rada Mihalcea
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
In this paper, we explore the task of predicting human activities from user-generated content.  ...  We train a neural network model to make predictions about which clusters contain activities that were performed by a given user based on the text of their previous posts and selfdescription.  ...  Conclusions In this paper, we addressed the task of predicting human activities from user-generated content.  ... 
doi:10.18653/v1/p19-1245 dblp:conf/acl/WilsonM19 fatcat:qeqzqt5odfcbpijziirl7nrmlu

Social Influence (Deep) Learning for Human Behavior Prediction [chapter]

Luca Luceri, Torsten Braun, Silvia Giordano
2018 Complex Networks IX  
We identified approximately 31K bots and characterized their activity in contrast with humans.  ...  The online ecosystem, however, does not only include human users but has given a space to an increasing number of automated accounts, referred to as bots, extensively used to spread messages and manipulate  ...  ") that received a large amount of retweets from bots (top 3 of bots-retweet from human generated content). This may indicate a combined approach leveraging both human and bot activities.  ... 
doi:10.1007/978-3-319-73198-8_22 fatcat:265ji3nqyzcylmpay4js3x7tti

Evolution of bot and human behavior during elections

Luca Luceri, Ashok Deb, Silvia Giordano, Emilio Ferrara
2019 First Monday  
We identified approximately 31K bots and characterized their activity in contrast with humans.  ...  The online ecosystem, however, does not only include human users but has given a space to an increasing number of automated accounts, referred to as bots, extensively used to spread messages and manipulate  ...  ") that received a large amount of retweets from bots (top 3 of bots-retweet from human generated content). This may indicate a combined approach leveraging both human and bot activities.  ... 
doi:10.5210/fm.v24i9.10213 fatcat:fz3vphnohjfihkzhdrog3rvudm

Activity-based Twitter sampling for content-based and user-centric prediction models

Somayyeh Aghababaei, Masoud Makrehchi
2017 Human-Centric Computing and Information Sciences  
The predictability of the collected content from activity-based and random sampling is compared in a content-based and user-centric temporal model.  ...  This vast amount of publicly available user-generated content is applied to many applications ranging from tracking human social behavior [2] [3] [4] , detecting events of interest [5] [6] [7] , to smart  ...  The predictability of the content extracted from active users was compared with the content retrieved from random users in two models: the content-based and user-centric approaches.  ... 
doi:10.1186/s13673-016-0084-z fatcat:vh6p45w4cbaynkoaimensumi2y

MAPer

Sarah Masud Preum, John A. Stankovic, Yanjun Qi
2015 Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15  
, and activities of daily living collected from a single resident and a multi-resident home.  ...  We demonstrate the effectiveness of MAPer on four real datasets representing different behavior domains, including, habitual behavior collected from Twitter, need based behavior collected from search logs  ...  Currently we are using only temporal footprint of activities. In the future, we want to model behavior by extracting textual features from user generated contents.  ... 
doi:10.1145/2806416.2806562 dblp:conf/cikm/PreumSQ15 fatcat:kciuhpl3kfeyha7d2zqx6hxg6a

Mining Social Data to Extract Intellectual Knowledge

Muhammad Mahbubur Rahman
2012 International Journal of Intelligent Systems and Applications  
We also analyze our mined knowledge with comparison for possible usages like as human behavior prediction, pattern recognition, job responsibility distribution, decision making and product promoting.  ...  This information can be used in relationship prediction, decision making, pat-tern recognition, social mapping, responsibility distri-bution and many other applications.  ...  Features Taking whole content from any text attribute and filtering the content by removing common words, keywords are generated.  ... 
doi:10.5815/ijisa.2012.10.02 fatcat:l4potmvadveavgquunbscs5s2m

"Is a picture really worth a thousand words?": A case study on classifying user attributes on Instagram

Junho Song, Kyungsik Han, Dongwon Lee, Sang-Wook Kim, Lidia Adriana Braunstein
2018 PLoS ONE  
We further demonstrate the robustness of our models using a new set of test data, with which the models exhibit greater overall performance than human raters.  ...  We demonstrate the strong influence of age and gender on Instagram use in terms of topical and content differences.  ...  Additionally, females tend to invest more effort in reciprocating social links and are more active and general in their content generation, whereas males tend to focus their posts on specific topics.  ... 
doi:10.1371/journal.pone.0204938 fatcat:abeoh4msdjh3tj7jbjpqzqfwv4

Dynamic Reputation Rating Mechanism for Social Content Curation Services

Jinhyung Cho, Hwansoo Kang, Seawoo Kim
2015 Indian Journal of Science and Technology  
preferences for users who have not evaluated many contents.  ...  Recently various social curation mechanisms have been developed to organize and suggest digital contents around one or more particular themes or topics for online users on Social Network Services (SNS)  ...  The content reputation rating process is a collaborative filtering process to predict general community users' evaluation ratings of each content item.  ... 
doi:10.17485/ijst/2015/v8i18/77714 fatcat:jt4qdgchlvalzdnm7od5taruw4

Understanding Smartphone Notifications' User Interactions and Content Importance

Aku Visuri, Niels van Berkel, Tadashi Okoshi, Jorge Goncalves, Vassilis Kostakos
2019 International Journal of Human-Computer Studies  
We assess the effectiveness of personalised prediction models generated using a combination of self-reported content importance and contextual information.  ...  We use a dataset of notifications received by 40 anonymous users in-the-wild, which consists of 1) qualitative user-labelled information about their preferences on notification's contents, 2) notification  ...  to periodically rate past notifications according to their content importance and timing of delivery. • Mode B -Predictive Modelling: After the user has rated 50 past notifications, he is asked to activate  ... 
doi:10.1016/j.ijhcs.2019.03.001 fatcat:mijk4s3n5zd7dczj5z5lurb3wi

A self-learning personalized feedback agent for motivating physical activity

Harm op den Akker, Laura S. Moualed, Valerie M. Jones, Hermie J. Hermens
2011 Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies - ISABEL '11  
We present a general approach for the implementation of an electronic Feedback Agent that serves as a personal coach for achieving and maintaining a healthy level of physical activity through sustainable  ...  An important aspect in the treatment of various chronic diseases is to optimise physical activity levels.  ...  Similarly, the content of the feedback message is generated based on statistical information used from other users predicted as similar to this user based on the clustering in step 1.  ... 
doi:10.1145/2093698.2093845 dblp:conf/isabel/AkkerMJH11 fatcat:wwprnu5kere5nkpbntk4xinfwe

Explainability via Responsibility [article]

Faraz Khadivpour, Matthew Guzdial
2020 arXiv   pre-print
This can be even more tricky in co-creative systems where human designers must interact with AI agents to generate game content.  ...  Procedural Content Generation via Machine Learning (PCGML) refers to a group of methods for creating game content (e.g. platformer levels, game maps, etc.) using machine learning models.  ...  Procedural Content Generation via Machine Learning (PCGML) Procedural Content Generation via Machine Learning (PCGML) is a field of research focused on the creation of game content by machine learning  ... 
arXiv:2010.01676v1 fatcat:khqyg5xgmjdwxbiqdiqkec6jne

Scaling-Laws of Human Broadcast Communication Enable Distinction between Human, Corporate and Robot Twitter Users

Gabriela Tavares, Aldo Faisal, Yamir Moreno
2013 PLoS ONE  
More importantly, we identify a characteristic power-law decrease in the tail of inter-message time distribution by human users which is different from that obtained for managed and automated accounts.  ...  To test our hypothesis, we investigate whether it is possible to differentiate between user types based on tweet timing behaviour, independently of the content in messages.  ...  Acknowledgments The authors would like to thank an anonymous reviewer for their valuable comments and suggestions, which have considerably improved the quality of our analysis and the paper in general.  ... 
doi:10.1371/journal.pone.0065774 pmid:23843945 pmcid:PMC3701018 fatcat:poeo7koav5ab3hywckapovxlti

A Novel Emotion-Aware Hybrid Music Recommendation Method Using Deep Neural Network

Shu Wang, Chonghuan Xu, Austin Shijun Ding, Zhongyun Tang
2021 Electronics  
However, conventional studies identified emotion as discrete representations, and could not predict users' emotional states at time points when no user activity data exists, let alone the awareness of  ...  Based on the models, we proposed a hybrid approach of combining content-based and collaborative filtering for generating emotion-aware music recommendations.  ...  Data Availability Statement: The data are available from the corresponding author on request. Conflicts of Interest: The authors claim that there is no conflict of interest.  ... 
doi:10.3390/electronics10151769 fatcat:ej2zxbjwb5c2popykdv3ezip6u

MoView Engine : An Open Source Movie Recommender

Vallari Manavi, Anjali Diwate, Priyanka Korade, Anita Senathi, V.A. Vyawahare, M.D. Patil
2020 ITM Web of Conferences  
It is the ability to think as a human brain as give the output best suited to the end users liking.  ...  This paper focuses on implementing the recommendation system of movies using deep learning with neural network model using the activation function of SoftMax to give an experience to users as friendly  ...  Predictions are generally done on the basis of human interests, behavior, personality etc. For any recommendation system to work properly it should know its audience.  ... 
doi:10.1051/itmconf/20203203008 fatcat:wpmaggl2nzah5cgnq3vhvapx6q

Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure [article]

Besmira Nushi, Ece Kamar, Eric Horvitz
2018 arXiv   pre-print
Pandora leverages both human and system-generated observations to summarize conditions of system malfunction with respect to the input content and system architecture.  ...  As machine learning systems move from computer-science laboratories into the open world, their accountability becomes a high priority problem.  ...  First, it clusters the input domain into topical clusters constructed either from human-generated content features or from automated system-generated features representing content.  ... 
arXiv:1809.07424v1 fatcat:llphstxqifcaloqqamefxkr5cy
« Previous Showing results 1 — 15 out of 280,049 results