Filters








8,604 Hits in 6.0 sec

DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums [article]

Yuyang Gao, Lingfei Wu, Houman Homayoun, Liang Zhao
2019 arXiv   pre-print
to specific health topics.  ...  In this paper, we first formulate the transition of user activities as a dynamic graph with multi-attributed nodes, then formalize the health stage inference task as a dynamic graph-to-sequence learning  ...  However, there are two issues with this simple sequence decoder: 1) the effectiveness of the sequence decoder depends on the length of the dynamic graph sequence; and 2) the predicted user's health stage  ... 
arXiv:1908.08497v1 fatcat:u2mc6ig7ubaofnr443rcjyweqa

Predicting Topic Participation by Jointly Learning User Intrinsic and Extrinsic Preference

Fan Zhou, Lei Liu, Kunpeng Zhang, Goce Trajcevski, Jin Wu
2019 IEEE Access  
on networks to predict the topics of potential interest.  ...  A specific aspect of interest is to predict which topics a particular user is more likely to be involved in.  ...  MULTI-LABEL CLASSIFIER FOR NEXT TOPIC PARICIPATION PREDICTION A user may be interested in more than one topic, we formulate the next topic participation prediction task as a multi-label classification  ... 
doi:10.1109/access.2019.2890826 fatcat:jtn3g6qczfh43eu55jrc5vzyju

Explainable Depression Detection with Multi-Modalities Using a Hybrid Deep Learning Model on Social Media [article]

Hamad Zogan, Imran Razzak, Xianzhi Wang, Shoaib Jameel, Guandong Xu
2021 arXiv   pre-print
In this work, we propose interpretive Multi-Modal Depression Detection with Hierarchical Attention Network MDHAN, for detection depressed users on social media and explain the model prediction.  ...  We also show that our model helps improve predictive performance when detecting depression in users who are posting messages publicly on social media.  ...  To the best of our knowledge, this is the first work of using multi-modalities of topical, temporal and semantic features jointly with word embeddings in deep learning for depression detection. (4) The  ... 
arXiv:2007.02847v2 fatcat:4y4xl7rysfdqtfj3pojqxk6zo4

Stance Detection on Social Media: State of the Art and Trends [article]

Abeer AlDayel, Walid Magdy
2020 arXiv   pre-print
This paper surveys the work on stance detection and situates its usage withincurrent opinion mining techniques in social media.  ...  most effective approaches.In addition, this study explores the emerging trends and the different applications of stance detection on social media.The study concludes by providing discussion of the gabs in  ...  This scarcity reflected by the need to enrich the data with information related to the object of interest.  ... 
arXiv:2006.03644v1 fatcat:hw3qqg2k3vbkjodef764c46ajy

Twitter User Representation Using Weakly Supervised Graph Embedding [article]

Tunazzina Islam, Dan Goldwasser
2022 arXiv   pre-print
In this paper, we propose a weakly supervised graph embedding based framework for understanding user types.  ...  We evaluate the user embedding learned using weak supervision over well-being related tweets from Twitter, focusing on 'Yoga', 'Keto diet'.  ...  In addition to the tweet, user's profile description and network are helpful.  ... 
arXiv:2108.08988v3 fatcat:twwzp2d435h2zdidwkddjrh2he

User Service Rating Prediction System by Exploring Social Users Rating Behavior

Skive Arasan
2017 International Journal for Research in Applied Science and Engineering Technology  
In the proposed system we fuse four factors they are, user personal interest(related to item's domain), interpersonal interest similarity between users(related to users interest), similarity in interpersonal  ...  In our point of view the rating behaviour in this system could be embedded with these aspects: 1) when user had rated the item, what is the rating of that item, 2) what is the item, 3) what are the rating  ...  With the in-formation embedded in the review text, we will alleviate the cold-start drawback. Furthermore, our model is able to be told latent topics that area unit explicable.  ... 
doi:10.22214/ijraset.2017.3232 fatcat:aehzxhb54re2tk73kxpkewprha

Social Media-based User Embedding: A Literature Review

Shimei Pan, Tao Ding
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
In this survey, we review typical methods for learning a unified user embeddings from heterogeneous user data (e.g., combines social media texts with images to learn a unified user representation).  ...  In this paper, we review recent advance in learning to represent social media users in low-dimensional embeddings.  ...  The learned embedding has been used to characterize a Twitter user's social network structure [Do et al., 2018] and predict user interests [Grover and Leskovec, 2016] .  ... 
doi:10.24963/ijcai.2019/881 dblp:conf/ijcai/PanD19 fatcat:inw55rewvzh5nckevzvrsexwii

Predicting Which Topics You Will Join in the Future on Social Media

Haoran Huang, Qi Zhang, Jindou Wu, Xuanjing Huang
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
User's posting history and topics were modeled with an external neural memory architecture. e convolutional neural network based matching methods were used to construct the relations between users and  ...  It also can be of great interest for many applications. In this study, we investigate the problem of predicting whether a user will join a topic based on his posting history.  ...  In contrast to the tweet recommendation task and early trend detection task, this task focuses on predicting the relations between users and topics; 2) we proposed a novel deep convolutional neural network  ... 
doi:10.1145/3077136.3080791 dblp:conf/sigir/HuangZWH17 fatcat:epvkau5cbfhdrcws3jiil4aykq

Multi-Interest-Aware User Modeling for Large-Scale Sequential Recommendations [article]

Jianxun Lian, Iyad Batal, Zheng Liu, Akshay Soni, Eun Yong Kang, Yajun Wang, Xing Xie
2021 arXiv   pre-print
SUM models user behavior with a multi-channel network, with each channel representing a different aspect of the user's interests.  ...  Traditional models tend to encode a user's behaviors into a single embedding vector, which do not have enough capacity to effectively capture her diverse interests.  ...  Similarly, [13, 18] design a multi-interest extractor layer with various dynamic routing mechanisms to extract user's diverse interests.  ... 
arXiv:2102.09211v3 fatcat:ko5u6yavh5h2ni4isnanhnieue

Rating Prediction based on Social Sentiment from Textual Reviews

R. G., S. R.
2019 International Journal of Computer Applications  
During this work, we have a tendency to propose a sentiment-based rating prediction methodology (RPS) to enhance prediction accuracy in recommender systems.  ...  In recent years, we've witnessed a flourish of review websites. It presents an excellent chance to share our viewpoints for numerous merchandise we have a tendency to purchase.  ...  Most topic models introduce users' interests as topic distributions in keeping with reviews contents. They're wide applied in sentiment analysis, travel recommendation, and social networks analysis.  ... 
doi:10.5120/ijca2019919085 fatcat:mbcizsubsbhgdejjllcloojlsm

Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation

Xin Dong, Jingchao Ni, Wei Cheng, Zhengzhang Chen, Bo Zong, Dongjin Song, Yanchi Liu, Haifeng Chen, Gerard De Melo
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this work, we develop a novel neural network model that properly accounts for this important difference by means of asymmetric attentive modules.  ...  In practice, however, these two sets of reviews are notably different: users' reviews reflect a variety of items that they have bought and are hence very heterogeneous in their topics, while an item's  ...  D-ATT (Seo et al. 2017 ) uses dual-attention based networks to learn embeddings, and a simple dot product to predict ratings.  ... 
doi:10.1609/aaai.v34i05.6268 fatcat:e5jz3ds57bfklduzz7sd3jwbai

Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation [article]

Xin Dong, Jingchao Ni, Wei Cheng, Zhengzhang Chen, Bo Zong, Dongjin Song, Yanchi Liu, Haifeng Chen, Gerard de Melo
2019 arXiv   pre-print
In this work, we develop a novel neural network model that properly accounts for this important difference by means of asymmetric attentive modules.  ...  In practice, however, these two sets of reviews are notably different: users' reviews reflect a variety of items that they have bought and are hence very heterogeneous in their topics, while an item's  ...  Related Work Exploiting reviews has proven considerably useful in recent work on recommendation. Many methods primarily focus on topic modeling based on the review texts.  ... 
arXiv:2001.04346v1 fatcat:dj2a6g4uqzfjpgd7uanx56l3v4

A survey on next location prediction techniques, applications, and challenges

Ayele Gobezie Chekol, Marta Sintayehu Fufa
2022 EURASIP Journal on Wireless Communications and Networking  
Furthermore, application and challenges are addressed related to the user's next location prediction.  ...  Recent growth of location-based service applications has vast domain influence such as traffic-flow prediction, weather forecast, and network resource optimization.  ...  [78] mined both the social networks and mobile trajectories in a neural network, in which they employed RNN to capture the sequential relatedness in mobile trajectories.  ... 
doi:10.1186/s13638-022-02114-6 fatcat:s2ixs3ftibaobighbik6ikgfce

Global Multi-Source Information Fusion Management and Deep Learning Optimization for Tourism

Xue Yu
2022 Journal of Organizational and End User Computing  
The semantic and emotional information in the comment text is extracted to identify user preferences, and the score of interest points in the target location is predicted combined with the influence factors  ...  Then, the interest point recommendation framework based on convolutional neural network (IPRC) is established.  ...  to identify potential topics of online health problems and match them with doctors' specialties.  ... 
doi:10.4018/joeuc.294902 fatcat:o5dym52ibrhfvgdsoiruz3efy4

Learning Representations of Social Media Users [article]

Adrian Benton
2018 arXiv   pre-print
Is the representation predictive of latent properties such as a person's demographic features, socioeconomic class, or mental health state? Is it predictive of the user's future behavior?  ...  We treat user representations - ground truth gender and mental health features - as auxiliary tasks to improve mental health state prediction.  ...  Suicide risk and related mental health conditions are therefore good candidates for modeling in a multi-task framework.  ... 
arXiv:1812.00436v1 fatcat:qp2hf6f6nfe7djyjakkns36epq
« Previous Showing results 1 — 15 out of 8,604 results