{"title":"POI recommendation with geographical and multi-tag influences","authors":"Zhiyuan Zhang, Yun Liu, Haiqiang Chen, Qing Liu","doi":"10.1109/BESC.2016.7804488","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804488","url":null,"abstract":"In this paper, we propose a method for point of interest (POI) recommendation by extracting the multi-tag influence and modeling the geographical influence. First of all, we extract a user-tag matrix from the initial user-POI rating matrix by analyzing the relations between POI and the related bag of tags. Secondly, we use the probabilistic factor model to predict the missing data of the extracted matrix. Thirdly, an effective method to model the geographical influence is proposed by considering the location of user and POI and the related region center. Finally, the multi-tag and geographical influence are fused in the process of making prediction of missing value of every POI. Then we will get a great result for POI recommendation. The experimental analysis on the large dataset Yelp demonstrates that our method outperform the state-of-art methods.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130090689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Interpolative self-training approach for sentiment analysis","authors":"S. Aghababaei, M. Makrehchi","doi":"10.1109/BESC.2016.7804475","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804475","url":null,"abstract":"Sentiment analysis has become one of the fundamental research areas with an objective of estimating the polarity of text documents. While sentiment analysis requires rich training resources, the number of available labeled documents is limited. The proposed interpolative self-training model is an extension of self-training as one of the most common semi-supervised learning algorithms. The proposed method is based on enlarging learning documents by interpolating data in both the training and the test phase. The method also includes a weighting strategy for data selection in each iteration. The method is evaluated using four Twitter datasets for the task of sentiment analysis. The results indicate that the proposed self-training model successfully outperforms the baseline and the standard self-training approach.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131414276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Classifying sybil in MSNs using C4.5","authors":"Anand Chinchore, Guandong Xu, F. Jiang","doi":"10.1109/BESC.2016.7804499","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804499","url":null,"abstract":"Sybil detection is an important task in cyber security research. Over past years, many data mining algorithms have been adopted to fulfill such task. Using classification and regression for sybil detection is a very challenging task. Despite of existing research made toward modeling classification for sybil detection and prediction, this research has proposed new solution on how sybil activity could be tracked to address this challenging issue. Prediction of sybil behaviour has been demonstrated by analysing the graph-based classification and regression techniques, using decision trees and described dependencies across different methods. Calculated gain and maxGain helped to trace some sybil users in the datasets.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"278 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124470814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Digital humanities as a cross-sector and cross-discipline initiative: Prospects in the Linnaeus University region","authors":"Koraljka Golub, M. Milrad","doi":"10.1109/BESC.2016.7804497","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804497","url":null,"abstract":"This position paper presents and analyses the cross-sector and cross-disciplinary Digital Humanities Initiative at Linnaeus University along the axes of its strengths, weaknesses, opportunities and threats. Our long-term vision is to create a leading education in this field and to establish a leading research regional centre that combines in novel ways already existing expertise from different departments and faculties working in close collaboration and co-creation with people and different organizations (both public and private sector) from the surrounding society.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128201014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Interactive exploration and understanding of contagion dynamics in networked populations","authors":"S. Abdelhamid, C. Kuhlman, M. Marathe, S. Ravi","doi":"10.1109/BESC.2016.7804480","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804480","url":null,"abstract":"Modeling and simulation of contagion processes on networked populations are used to understand protests, social unrest, the spread of information, and virus and disease epidemics, among other phenomena. Network structure and attributes of vertices and edges are often useful in explaining contagion spreading processes. However, particularly for larger networks (e.g., those with hundreds of thousands or millions of vertices), reasoning about and making sense of contagion propagation results is difficult owing to the scale of these simulations. We present a web application called NEMO for assisting an analyst in understanding contagion processes and in establishing causality. It has several features to query and visualize networks, subnetworks, and their properties. In addition to explaining NEMO's features, we provide a real case study of the spread of Ebola on a 4-million-vertex social network of Liberia, Africa. We demonstrate how NEMO can be used to explore interactively networks to understand the reasons for the effectiveness of different interventions.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123868819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Coupled feature spaces learning with joint graph regularization for person re-identification","authors":"Peng Bian, Yi Jin, Luyue Jiang, Yidong Li","doi":"10.1109/BESC.2016.7804501","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804501","url":null,"abstract":"Re-identification of individuals has already drawn growing attentions due to the increasing intelligent visual surveillance. Human signature is quite different over a network of cameras and most related work devotes to selecting human features without any distinction. To address the problem, we propose a novel coupled feature space learning with joint graph regularization in this paper. The proposed method aims to learn a joint graph regularized common feature space in which two projection matrices can be matched. In the procedure, we use l21-norm to select relevant and discriminative features from coupled space simultaneously. A joint graph regular term enhances the relevance of different photos from the same person. Comparisons results show the superiority and efficiency of our proposed method with performance measured in terms of Cumulative Match Characteristic curves (CMC) on three challenging datasets.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114736753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jianbo Gao, Matthew L. Jockers, John Laudun, Timothy R. Tangherlini
{"title":"A multiscale theory for the dynamical evolution of sentiment in novels","authors":"Jianbo Gao, Matthew L. Jockers, John Laudun, Timothy R. Tangherlini","doi":"10.1109/BESC.2016.7804470","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804470","url":null,"abstract":"Recent work in literary sentiment analysis has suggested that shifts in emotional valence may serve as a reliable proxy for plot movement in novels. The raw sentiment time series of a novel can now be extracted using a variety of different methods, and after extraction, filtering is commonly used to smooth the irregular sentiment time series. Using an adaptive filter, which is among the most effective in determining trends of a signal, reducing noise, and performing fractal and multifractal analysis, we show that the energy of the smoothed sentiment signals decays with the smoothing parameter as a power-law, characterized by a Hurst parameter H of 1/2 <; H <; 1, which signifies long-range correlations. We further show that a smoothed sentiment arc corresponds to the sentiment of fast playing mode or sentiment retained in one's memory, and that for a novel to be both captivating and rich, H has to be larger than 1/2 but cannot be too close to 1.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115114650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shi Shen, Changxiu Cheng, Kai Su, J. Yang, Shanli Yang
{"title":"Quantitative visualization about differences between scientists concerned nature disasters and historic events","authors":"Shi Shen, Changxiu Cheng, Kai Su, J. Yang, Shanli Yang","doi":"10.1109/BESC.2016.7804495","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804495","url":null,"abstract":"How to process massive historic natural disasters events is a great challenge to recognize patterns. And more and more scientific research data provides a new source of nature disasters. In this study, the biclustering method is used to categorize the scientists concerned natural disasters and historic events. Cartograms, one kind of transformed maps, are created to highlight numbers of publications and events in a country. Reaction index (RI) is introduced to evaluate the difference between scientists concerned nature disasters and historic events. The results show that biclustering is a useful method to categorize data with high volumes and dimensions. Cartograms could represent conceptual patterns that are difficult to be displayed in regular maps. Analysis indicates that earthquakes and landslides attract relatively more concerns from scientists in the north hemisphere; floods are more focused by scientists in the south hemisphere. Although droughts are not significant in the cartogram of historic events, they obtain attentions from scientists of inland as well. The distribution of RIs shows that more scientists need to put more efforts in dealing with natural disasters, especially in Indonesia and Philippines.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121278103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Overlapping community detection via self-constrained symmetric non-negative matrix factorization","authors":"Yu Liu, Bin Wu, Yunlei Zhang, Bai Wang","doi":"10.1109/BESC.2016.7804477","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804477","url":null,"abstract":"A number of approaches based on symmetric nonnegative matrix factorization (SNMF) have been proposed to improve the performance and the interpretability of community detection. Due to the nature of NMF, the partition results obtained by conventional NMF without post processing are soft assignments of nodes w.r.t. communities, which demonstrates overlapping of communities. Based on the traditional SNMF method, we propose a self-constrained symmetric non-negative matrix factorization (SC-SNMF) with tuning ability to control the degree of community overlapping, which controls if the community partition result is \"most overlapping\", \"nearly overlapping\" or \"nearly non-overlapping\". We use both traditional and overlapping version of modularity and partition density to investigate community overlapping on five real-world social network datasets. The experimental results show that SCSNMF has the ability of interpretation for overlapping degree of communities.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132432196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Research on fire risk factors of cotton in railway transportation","authors":"Yaxin Hou, Cong Ma, Yidong Li","doi":"10.1109/BESC.2016.7804490","DOIUrl":"https://doi.org/10.1109/BESC.2016.7804490","url":null,"abstract":"Cotton plays a very important role in the economy of China and wellbeing of millions of people depends upon its good production and utilization in the country. Therefore, the railway transportation of cotton is becoming more and more important. In this paper, we analyze main factors causing cotton fire according to historical information. We first calculate the relative importance of all features for the risk of catching fire with the clustering method. Then, we calculate the risk rate of each main factor. The experiments show that the inside temperature of cabin, and the humidity and inside temperature of cotton pack are the top three factors that may cause fire.","PeriodicalId":225942,"journal":{"name":"2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)","volume":"410 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132313942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}