Philipp Berger, Patrick Hennig, Tom Bocklisch, Tom Herold, C. Meinel
Question and Answering (Q&A) platforms are an important source for information and a first place to go when searching for help. Q&A sites, like StackOverflow (SO), use reward systems to incentivize users to answer fast and accurately. In this paper we study and predict the response time for those questions on StackOverflow, that benefit from an additional incentive through so called bounties. Shaped by different motivations and rules these questions perform unlike regular questions. As our key finding we note that topic related factors provide a much stronger evidence than previously found factors for these questions. Finally, we compare models based on these features predicting the response time in the context of bounty questions.
{"title":"A Journey of Bounty Hunters: Analyzing the Influence of Reward Systems on StackOverflow Question Response Times","authors":"Philipp Berger, Patrick Hennig, Tom Bocklisch, Tom Herold, C. Meinel","doi":"10.1109/WI.2016.0114","DOIUrl":"https://doi.org/10.1109/WI.2016.0114","url":null,"abstract":"Question and Answering (Q&A) platforms are an important source for information and a first place to go when searching for help. Q&A sites, like StackOverflow (SO), use reward systems to incentivize users to answer fast and accurately. In this paper we study and predict the response time for those questions on StackOverflow, that benefit from an additional incentive through so called bounties. Shaped by different motivations and rules these questions perform unlike regular questions. As our key finding we note that topic related factors provide a much stronger evidence than previously found factors for these questions. Finally, we compare models based on these features predicting the response time in the context of bounty questions.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"15 1","pages":"644-649"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85779266","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}
Qiong Wu, Siyuan Liu, C. Miao, Y. Liu, Cyril Leung
With the prevalence of social networks, social recommendation is rapidly gaining popularity. Currently, social information has mainly been utilized for enhancing rating prediction accuracy, which may not be enough to satisfy user needs. Items with high prediction accuracy tend to be the ones that users are familiar with and may not interest them to explore. In this paper, we take a psychologically inspired view to recommend items that will interest users based on the theory of social curiosity and study its impact on important dimensions of recommender systems. We propose a social curiosity inspired recommendation model which combines both user preferences and user curiosity. The proposed recommendation model is evaluated using large scale real world datasets and the experimental results demonstrate that the inclusion of social curiosity significantly improves recommendation precision, coverage and diversity.
{"title":"A Social Curiosity Inspired Recommendation Model to Improve Precision, Coverage and Diversity","authors":"Qiong Wu, Siyuan Liu, C. Miao, Y. Liu, Cyril Leung","doi":"10.1109/WI.2016.0042","DOIUrl":"https://doi.org/10.1109/WI.2016.0042","url":null,"abstract":"With the prevalence of social networks, social recommendation is rapidly gaining popularity. Currently, social information has mainly been utilized for enhancing rating prediction accuracy, which may not be enough to satisfy user needs. Items with high prediction accuracy tend to be the ones that users are familiar with and may not interest them to explore. In this paper, we take a psychologically inspired view to recommend items that will interest users based on the theory of social curiosity and study its impact on important dimensions of recommender systems. We propose a social curiosity inspired recommendation model which combines both user preferences and user curiosity. The proposed recommendation model is evaluated using large scale real world datasets and the experimental results demonstrate that the inclusion of social curiosity significantly improves recommendation precision, coverage and diversity.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"27 1","pages":"240-247"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79023113","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}
Core periphery structure is a meso-scale property of complex networks. Core periphery structures can help identify the relationships between cohesive core clusters surrounded by sparse peripheries. The knowledge about such relationships can have many practical applications in real world complex networks. For example, in a web based network between all blogs on different topics, peripheries connecting popular groups could help in the study of flow of information across the web. In this paper, we propose a construction of core periphery structures for weighted graphs. We present a greedy growth based algorithm to extract core periphery structures in weighted graphs. We also score the core periphery associations as a measure of distance between them. Through extensive experimentation using two synthetic and two real world Protein-Protein Interaction (PPI) networks, we demonstrate the usefulness of core periphery structures over simple overlapping clusters obtained by a state of the art clustering algorithm called ClusterONE.
{"title":"Core Periphery Structures in Weighted Graphs Using Greedy Growth","authors":"D. Sardana, R. Bhatnagar","doi":"10.1109/WI.2016.0012","DOIUrl":"https://doi.org/10.1109/WI.2016.0012","url":null,"abstract":"Core periphery structure is a meso-scale property of complex networks. Core periphery structures can help identify the relationships between cohesive core clusters surrounded by sparse peripheries. The knowledge about such relationships can have many practical applications in real world complex networks. For example, in a web based network between all blogs on different topics, peripheries connecting popular groups could help in the study of flow of information across the web. In this paper, we propose a construction of core periphery structures for weighted graphs. We present a greedy growth based algorithm to extract core periphery structures in weighted graphs. We also score the core periphery associations as a measure of distance between them. Through extensive experimentation using two synthetic and two real world Protein-Protein Interaction (PPI) networks, we demonstrate the usefulness of core periphery structures over simple overlapping clusters obtained by a state of the art clustering algorithm called ClusterONE.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"49 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87631253","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}
With the development of pattern recognition and artificial intelligence, emotion recognition based on facial expression has attracted a great deal of research interest. Facial emotion recognition are mainly based on facial images. The commonly used datasets are created artificially, with obvious facial expression on each facial images. Actually, emotion is a complicated and dynamic process. If a person is happy, probably he/she may not keep obvious happy facial expression all the time. Practically, it is important to recognize emotion correctly even if the facial expression is not clear. In this paper, we propose a new method of emotion recognition, i.e., to identify three kinds of emotion: sad, happy and neutral. We acquire 1347 3D facial points by Kinect V2.0. Key facial points are selected and feature extraction is conducted. Principal Component Analysis (PCA) is employed for feature dimensionality reduction. Several classical classifiers are used to construct emotion recognition models. The best performance of classification on all, male and female data are 70%, 77% and 80% respectively.
{"title":"Emotion Detection Using Kinect 3D Facial Points","authors":"Zhan Zhang, Liqing Cui, Xiaoqian Liu, T. Zhu","doi":"10.1109/WI.2016.0063","DOIUrl":"https://doi.org/10.1109/WI.2016.0063","url":null,"abstract":"With the development of pattern recognition and artificial intelligence, emotion recognition based on facial expression has attracted a great deal of research interest. Facial emotion recognition are mainly based on facial images. The commonly used datasets are created artificially, with obvious facial expression on each facial images. Actually, emotion is a complicated and dynamic process. If a person is happy, probably he/she may not keep obvious happy facial expression all the time. Practically, it is important to recognize emotion correctly even if the facial expression is not clear. In this paper, we propose a new method of emotion recognition, i.e., to identify three kinds of emotion: sad, happy and neutral. We acquire 1347 3D facial points by Kinect V2.0. Key facial points are selected and feature extraction is conducted. Principal Component Analysis (PCA) is employed for feature dimensionality reduction. Several classical classifiers are used to construct emotion recognition models. The best performance of classification on all, male and female data are 70%, 77% and 80% respectively.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"3 2","pages":"407-410"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91474543","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}
In recent years, the amount of entities in large knowledge bases has been increasing rapidly. Such entities can help to bridge unstructured text with structured knowledge and thus be beneficial for many entity-centric applications. The key issue is to link entity mentions in text with entities in knowledge bases, where the main challenge lies in mention ambiguity. Many methods have been proposed to tackle this problem. However, most of the methods assume certain characteristics of the input mentions and documents, e.g., only named entities are considered. In this paper, we propose a context-aware approach to collective entity disambiguation of the input mentions in text with different characteristics in a consistent manner. We extensively evaluate the performance of our approach over 9 datasets and compare it with 14 state-of-the-art methods. Experimental results show that our approach outperforms the existing methods in most cases.
{"title":"Context-Aware Entity Disambiguation in Text Using Markov Chains","authors":"Lei Zhang, Achim Rettinger, Patrick Philipp","doi":"10.1109/WI.2016.0018","DOIUrl":"https://doi.org/10.1109/WI.2016.0018","url":null,"abstract":"In recent years, the amount of entities in large knowledge bases has been increasing rapidly. Such entities can help to bridge unstructured text with structured knowledge and thus be beneficial for many entity-centric applications. The key issue is to link entity mentions in text with entities in knowledge bases, where the main challenge lies in mention ambiguity. Many methods have been proposed to tackle this problem. However, most of the methods assume certain characteristics of the input mentions and documents, e.g., only named entities are considered. In this paper, we propose a context-aware approach to collective entity disambiguation of the input mentions in text with different characteristics in a consistent manner. We extensively evaluate the performance of our approach over 9 datasets and compare it with 14 state-of-the-art methods. Experimental results show that our approach outperforms the existing methods in most cases.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"19 1","pages":"49-56"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86103384","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}
Twitter has become key for bringing awareness about real-world events, but the identification of event related posts goes beyond filtering keywords. Semantic enrichment using knowledge sources such as the Linked Open Data (LOD) cloud, has been proposed to deal with the poor textual contents of tweets for event classification. However, each work considers a particular type of event, underlined by specific assumptions according to the application purpose. In a search for an approach that suits different types of events, in this paper we identify different types of semantic features, and propose a process for semantic enrichment that involves the mapping of textual tokens into semantic concepts, the extraction of corresponding semantic properties from the LOD cloud, and their interpolation for event classification. We evaluate the contribution of each type of semantic feature using different tweet datasets representing events of distinct natures, and knowledge extracted from DBPedia.
{"title":"Experiments with Semantic Enrichment for Event Classification in Tweets","authors":"Simone Aparecida Pinto Romero, Karin Becker","doi":"10.1109/WI.2016.0084","DOIUrl":"https://doi.org/10.1109/WI.2016.0084","url":null,"abstract":"Twitter has become key for bringing awareness about real-world events, but the identification of event related posts goes beyond filtering keywords. Semantic enrichment using knowledge sources such as the Linked Open Data (LOD) cloud, has been proposed to deal with the poor textual contents of tweets for event classification. However, each work considers a particular type of event, underlined by specific assumptions according to the application purpose. In a search for an approach that suits different types of events, in this paper we identify different types of semantic features, and propose a process for semantic enrichment that involves the mapping of textual tokens into semantic concepts, the extraction of corresponding semantic properties from the LOD cloud, and their interpolation for event classification. We evaluate the contribution of each type of semantic feature using different tweet datasets representing events of distinct natures, and knowledge extracted from DBPedia.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"52 1","pages":"503-506"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86765588","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}
Data fusion has been shown to be a simple and effective way to improve retrieval results. Most existing data fusion methods combine ranked lists from different retrieval functions for a single given query—but in most real search settings, the diversity of retrieval functions required to achieve good fusion performance is not available. This paper presents a method for data fusion based on combining ranked lists from different queries that users could have entered for their information need, keeping the retrieval function fixed. We argue that if we can obtain a set of "possible queries" for an information need, we can achieve high effectiveness by fusing the rankings over the possible queries. In order to demonstrate effectiveness, we present experimental results on 5 different datasets covering tasks such as ad-hoc search, novelty and diversity search, and search in the presence of implicit user feedback. Our results show strong performances for our method, it is competitive with state-of-the-art methods on the same datasets, and in some cases outperforms them.
{"title":"Fusing Search Results from Possible Alternative Queries","authors":"Ashraf Bah Rabiou, Ben Carterette","doi":"10.1109/WI.2016.0105","DOIUrl":"https://doi.org/10.1109/WI.2016.0105","url":null,"abstract":"Data fusion has been shown to be a simple and effective way to improve retrieval results. Most existing data fusion methods combine ranked lists from different retrieval functions for a single given query—but in most real search settings, the diversity of retrieval functions required to achieve good fusion performance is not available. This paper presents a method for data fusion based on combining ranked lists from different queries that users could have entered for their information need, keeping the retrieval function fixed. We argue that if we can obtain a set of \"possible queries\" for an information need, we can achieve high effectiveness by fusing the rankings over the possible queries. In order to demonstrate effectiveness, we present experimental results on 5 different datasets covering tasks such as ad-hoc search, novelty and diversity search, and search in the presence of implicit user feedback. Our results show strong performances for our method, it is competitive with state-of-the-art methods on the same datasets, and in some cases outperforms them.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"29 1","pages":"606-609"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81210164","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}
Social media provides increasing opportunities for users to voluntarily share their thoughts and concerns in a large volume of data. While user-generated data from each individual may not provide considerable information, when combined, they include hidden variables, which may convey significant events. In this paper, we pursue the question of whether social media context can provide socio-behavior "signals" for crime prediction. The hypothesis is that crowd publicly available data in social media, in particular Twitter, may include predictive variables, which can indicate the changes in crime rates. We developed a model for crime trend prediction where the objective is to employ Twitter content to identify whether crime rates have dropped or increased for the prospective time frame. We also present a Twitter sampling model to collect historical data to avoid missing data over time. The prediction model was evaluated for different cities in the United States. The experiments revealed the correlation between features extracted from the content and crime rate directions. Overall, the study provides insight into the correlation of social content and crime trends as well as the impact of social data in providing predictive indicators.
{"title":"Mining Social Media Content for Crime Prediction","authors":"S. Aghababaei, M. Makrehchi","doi":"10.1109/WI.2016.0089","DOIUrl":"https://doi.org/10.1109/WI.2016.0089","url":null,"abstract":"Social media provides increasing opportunities for users to voluntarily share their thoughts and concerns in a large volume of data. While user-generated data from each individual may not provide considerable information, when combined, they include hidden variables, which may convey significant events. In this paper, we pursue the question of whether social media context can provide socio-behavior \"signals\" for crime prediction. The hypothesis is that crowd publicly available data in social media, in particular Twitter, may include predictive variables, which can indicate the changes in crime rates. We developed a model for crime trend prediction where the objective is to employ Twitter content to identify whether crime rates have dropped or increased for the prospective time frame. We also present a Twitter sampling model to collect historical data to avoid missing data over time. The prediction model was evaluated for different cities in the United States. The experiments revealed the correlation between features extracted from the content and crime rate directions. Overall, the study provides insight into the correlation of social content and crime trends as well as the impact of social data in providing predictive indicators.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"31 1","pages":"526-531"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88169216","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}
Ameeta Agrawal, Raghavender Sahdev, Heydar Davoudi, Forouq Khonsari, Aijun An, Susan McGrath
Forced migration is increasingly becoming a global issue of concern. In this paper, we present an effective model of targeted event detection, as an essential step towards the forced migration detection problem. To date, most of the the approaches deal with the event detection in a general setting with the main objective of detecting the presence or onset of an event. However, we focus on analyzing the magnitude of a given event from a collection of text documents such as news articles from multiple sources. We use violence as an illustration as it is one of the most critical factors of forced migration. The recent advancements in semantic similarity measures are adopted to obtain relevant violence scores for each word in the vocabulary of news articles in an unsupervised manner. The resulting scores are then used to compute the average daily violence scores over a period of three months. Evaluation of the proposed model against a manually annotated data set yields a Pearson's correlation of 0.8. We also include a case study exploring the relationship between violence and key events.
{"title":"Detecting the Magnitude of Events from News Articles","authors":"Ameeta Agrawal, Raghavender Sahdev, Heydar Davoudi, Forouq Khonsari, Aijun An, Susan McGrath","doi":"10.1109/WI.2016.0034","DOIUrl":"https://doi.org/10.1109/WI.2016.0034","url":null,"abstract":"Forced migration is increasingly becoming a global issue of concern. In this paper, we present an effective model of targeted event detection, as an essential step towards the forced migration detection problem. To date, most of the the approaches deal with the event detection in a general setting with the main objective of detecting the presence or onset of an event. However, we focus on analyzing the magnitude of a given event from a collection of text documents such as news articles from multiple sources. We use violence as an illustration as it is one of the most critical factors of forced migration. The recent advancements in semantic similarity measures are adopted to obtain relevant violence scores for each word in the vocabulary of news articles in an unsupervised manner. The resulting scores are then used to compute the average daily violence scores over a period of three months. Evaluation of the proposed model against a manually annotated data set yields a Pearson's correlation of 0.8. We also include a case study exploring the relationship between violence and key events.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"47 1","pages":"177-184"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78737292","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}
In this paper we present an overview of our proposed algorithms for classifying regions of web pages based on content and visual properties. We show how hidden Markov trees may be effective for the classification and how this may end up offering improved experiences to users who are trying to view webpages.
{"title":"Classification via Hidden Markov Trees for a Vision-Based Approach to Conveying Webpages to Users with Assistive Needs","authors":"M. Cormier, R. Mann, R. Cohen, Karyn Moffatt","doi":"10.1109/WI.2016.0124","DOIUrl":"https://doi.org/10.1109/WI.2016.0124","url":null,"abstract":"In this paper we present an overview of our proposed algorithms for classifying regions of web pages based on content and visual properties. We show how hidden Markov trees may be effective for the classification and how this may end up offering improved experiences to users who are trying to view webpages.","PeriodicalId":6513,"journal":{"name":"2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"1 1","pages":"695-700"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90744579","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：