R. Santos, Sumit Shah, F. Chen, Arnold P. Boedihardjo, Chang-Tien Lu, Naren Ramakrishnan
Storytelling, the act of connecting entities through relationships, provides an intuitive platform for exploratory analysis. This paper combines storytelling and Spatio-logical Inference (SLI) to generate rules of interaction among entities and measure how well they forecast a real-world event. The proposed algorithm first takes as input the probability of prior occurrences of events along with their spatial distances. It calculates their soft truths, i.e., the belief they have indeed been observed with certainty. Subsequently, the algorithm applies a relaxed form of logical conjunction and disjunction to compute a distance to satisfaction for each rule. The rules of lowest distances represent the best forecasts. Extensive experiments with social unrest in Afghanistan show that storytelling and SLI can outperform common probabilistic approaches by as much as 30% in terms of precision and 13% in terms of recall.
{"title":"Forecasting location-based events with spatio-temporal storytelling","authors":"R. Santos, Sumit Shah, F. Chen, Arnold P. Boedihardjo, Chang-Tien Lu, Naren Ramakrishnan","doi":"10.1145/2755492.2755496","DOIUrl":"https://doi.org/10.1145/2755492.2755496","url":null,"abstract":"Storytelling, the act of connecting entities through relationships, provides an intuitive platform for exploratory analysis. This paper combines storytelling and Spatio-logical Inference (SLI) to generate rules of interaction among entities and measure how well they forecast a real-world event. The proposed algorithm first takes as input the probability of prior occurrences of events along with their spatial distances. It calculates their soft truths, i.e., the belief they have indeed been observed with certainty. Subsequently, the algorithm applies a relaxed form of logical conjunction and disjunction to compute a distance to satisfaction for each rule. The rules of lowest distances represent the best forecasts. Extensive experiments with social unrest in Afghanistan show that storytelling and SLI can outperform common probabilistic approaches by as much as 30% in terms of precision and 13% in terms of recall.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121116513","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}
Hansi Senaratne, A. Bröring, T. Schreck, Dominic Lehle
Today, a tremendous source of spatio-temporal data is user generated, so-called volunteered geographic information (VGI). Among the many VGI sources, microblogged services, such as Twitter, are extensively used to disseminate information on a near real-time basis. Interest in analysis of microblogged data has been motivated to date by many applications ranging from trend detection, early disaster warning, to urban management and marketing. One important analysis perspective in understanding microblogged data is based on the notion of drift, considering a gradual change of real world phenomena observed across space, time, content, or a combination thereof. The scientific contribution provided by this paper is the presentation of a systematic framework that utilises on the one hand a Kernel Density Estimation (KDE) to detect hotspot clusters of Tweeter activities, which are episodically sequential in nature. These clusters help to derive spatial trajectories. On the other hand we introduce the concept of drift that characterises these trajectories by looking into changes of sentiment and topics to derive meaningful information. We apply our approach to a Twitter dataset comprising 26,000 tweets. We demonstrate how phenomena of interest can be detected by our approach. As an example, we use our approach to detect the locations of Lady Gaga's concert tour in 2013. A set of visualisations allows to analyse the identified trajectories in space, enhanced by optional overlays for sentiment or other parameters of interest.
{"title":"Moving on Twitter: using episodic hotspot and drift analysis to detect and characterise spatial trajectories","authors":"Hansi Senaratne, A. Bröring, T. Schreck, Dominic Lehle","doi":"10.1145/2755492.2755497","DOIUrl":"https://doi.org/10.1145/2755492.2755497","url":null,"abstract":"Today, a tremendous source of spatio-temporal data is user generated, so-called volunteered geographic information (VGI). Among the many VGI sources, microblogged services, such as Twitter, are extensively used to disseminate information on a near real-time basis. Interest in analysis of microblogged data has been motivated to date by many applications ranging from trend detection, early disaster warning, to urban management and marketing. One important analysis perspective in understanding microblogged data is based on the notion of drift, considering a gradual change of real world phenomena observed across space, time, content, or a combination thereof.\u0000 The scientific contribution provided by this paper is the presentation of a systematic framework that utilises on the one hand a Kernel Density Estimation (KDE) to detect hotspot clusters of Tweeter activities, which are episodically sequential in nature. These clusters help to derive spatial trajectories. On the other hand we introduce the concept of drift that characterises these trajectories by looking into changes of sentiment and topics to derive meaningful information. We apply our approach to a Twitter dataset comprising 26,000 tweets. We demonstrate how phenomena of interest can be detected by our approach. As an example, we use our approach to detect the locations of Lady Gaga's concert tour in 2013. A set of visualisations allows to analyse the identified trajectories in space, enhanced by optional overlays for sentiment or other parameters of interest.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133732994","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}
Weibo is the premier microblog service in China, which is nicknamed as the "Chinese Twitter". Weibo messages consist of text messages, short links, images, audio and video. Its text is restricted to 140 Chinese characters. Since Twitter is blocked in the mainland of China, Weibo is the dominant microblog service in China. The dominance of Weibo in China makes it an obvious choice for capturing late breaking news. This paper describes the implementation of a system for capturing messages corresponding to late breaking news as well as a visualization tool that can display Weibo news messages on a map interface. There are several technical challenges to building this system. First, methods to automatically recognize and disambiguate geographical locations in messages written in Chinese. Second, due to the lack of a free accessible real-time streaming API as that similar to the Twitter Public Streaming API, a new strategy to collect the most recent news-related Weibo messages is devised. The system also uses news from Chinese news RSS feeds as complementary sources.
{"title":"WeiboStand: capturing Chinese breaking news using Weibo \"tweets\"","authors":"Cheng Fu, H. Samet, Jagan Sankaranarayanan","doi":"10.1145/2755492.2755499","DOIUrl":"https://doi.org/10.1145/2755492.2755499","url":null,"abstract":"Weibo is the premier microblog service in China, which is nicknamed as the \"Chinese Twitter\". Weibo messages consist of text messages, short links, images, audio and video. Its text is restricted to 140 Chinese characters. Since Twitter is blocked in the mainland of China, Weibo is the dominant microblog service in China. The dominance of Weibo in China makes it an obvious choice for capturing late breaking news. This paper describes the implementation of a system for capturing messages corresponding to late breaking news as well as a visualization tool that can display Weibo news messages on a map interface. There are several technical challenges to building this system. First, methods to automatically recognize and disambiguate geographical locations in messages written in Chinese. Second, due to the lack of a free accessible real-time streaming API as that similar to the Twitter Public Streaming API, a new strategy to collect the most recent news-related Weibo messages is devised. The system also uses news from Chinese news RSS feeds as complementary sources.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129877353","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}
Choosing a location for vacations and weekends usually confuses many people. This concern has attracted considerable attention in recent years as currently there is no application based on actual visitors that helps people in finding out the top places for vacations. Online social networks such as Twitter are becoming very popular in last few years and can help in this regard. People nowadays generally do check-ins at new places. Also, analysis of tweets tagged with geolocation and time can provide trends of top vacation spots. In this paper, we present VacationFinder; a novel location-based application that uses geotagged tweets to help people in where they should spend their holidays and weekends. We use real Twitter data crawled since October 2013. We apply indexing, spatio-temporal querying, and machine learning techniques to check, analyze, and filter the user activities in a particular country before and after a specific holiday. We then visualize the results and give our recommendations of top vacation spots for a particular holiday. The paper includes use cases on top vacation spots for Saudis in spring break of 2014 both inside as well as outside Saudi Arabia. Our application can not only help people but can also give direction to governmental agencies about promoting tourism in the country. It can also help law enforcement agencies, advertisement industry, and various businesses such as restaurants and shopping stores about where to focus during a particular holiday.
{"title":"VacationFinder: a tool for collecting, analyzing, and visualizing geotagged Twitter data to find top vacation spots","authors":"Jalal S. Alowibdi, Sohaib Ghani, M. Mokbel","doi":"10.1145/2755492.2755495","DOIUrl":"https://doi.org/10.1145/2755492.2755495","url":null,"abstract":"Choosing a location for vacations and weekends usually confuses many people. This concern has attracted considerable attention in recent years as currently there is no application based on actual visitors that helps people in finding out the top places for vacations. Online social networks such as Twitter are becoming very popular in last few years and can help in this regard. People nowadays generally do check-ins at new places. Also, analysis of tweets tagged with geolocation and time can provide trends of top vacation spots. In this paper, we present VacationFinder; a novel location-based application that uses geotagged tweets to help people in where they should spend their holidays and weekends. We use real Twitter data crawled since October 2013. We apply indexing, spatio-temporal querying, and machine learning techniques to check, analyze, and filter the user activities in a particular country before and after a specific holiday. We then visualize the results and give our recommendations of top vacation spots for a particular holiday. The paper includes use cases on top vacation spots for Saudis in spring break of 2014 both inside as well as outside Saudi Arabia. Our application can not only help people but can also give direction to governmental agencies about promoting tourism in the country. It can also help law enforcement agencies, advertisement industry, and various businesses such as restaurants and shopping stores about where to focus during a particular holiday.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123343585","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}
A number of natural language processing and text-mining algorithms have been developed to extract the geospatial cues (e.g., place names) to infer locations of content creators from publicly available information, such as text content, online social profiles, and the behaviors or interactions of users from social networks. These studies, however, can only successfully infer user locations at city levels with relatively decent accuracy, while much higher resolution is required for meaningful spatiotemporal analysis in geospatial fields. Additionally, geographical cues exploited by current text-based approaches are hidden in the unreliable, unstructured, informal, ungrammatical, and multilingual data, and therefore are hard to extract and make meaningful correctly. Instead of using such hidden geographic cues, this paper develops a GIS approach that can infer the true origin of tweets down to the zip code level by using and mining spatial (geo-tags) and temporal (timestamps when a message was posted) information recorded on user digital footprints. Further, individual major daily activity zones and mobility can be successfully inferred and predicted. By integrating GIS data and spatiotemporal clustering methods, this proposed approach can infer individual daily physical activity zones with spatial resolution as high as 20 m by 20 m or even higher depending on the number of digit footprints collected for social media users. The research results with detailed spatial resolution are necessary and useful for various applications such as human mobility pattern analysis, business site selection, disease control, or transportation systems improvement.
{"title":"From where do tweets originate?: a GIS approach for user location inference","authors":"Qunying Huang, G. Cao, Caixia Wang","doi":"10.1145/2755492.2755494","DOIUrl":"https://doi.org/10.1145/2755492.2755494","url":null,"abstract":"A number of natural language processing and text-mining algorithms have been developed to extract the geospatial cues (e.g., place names) to infer locations of content creators from publicly available information, such as text content, online social profiles, and the behaviors or interactions of users from social networks. These studies, however, can only successfully infer user locations at city levels with relatively decent accuracy, while much higher resolution is required for meaningful spatiotemporal analysis in geospatial fields. Additionally, geographical cues exploited by current text-based approaches are hidden in the unreliable, unstructured, informal, ungrammatical, and multilingual data, and therefore are hard to extract and make meaningful correctly. Instead of using such hidden geographic cues, this paper develops a GIS approach that can infer the true origin of tweets down to the zip code level by using and mining spatial (geo-tags) and temporal (timestamps when a message was posted) information recorded on user digital footprints. Further, individual major daily activity zones and mobility can be successfully inferred and predicted. By integrating GIS data and spatiotemporal clustering methods, this proposed approach can infer individual daily physical activity zones with spatial resolution as high as 20 m by 20 m or even higher depending on the number of digit footprints collected for social media users. The research results with detailed spatial resolution are necessary and useful for various applications such as human mobility pattern analysis, business site selection, disease control, or transportation systems improvement.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125076743","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}
Kyoung-Sook Kim, Hirotaka Ogawa, Akihito Nakamura, I. Kojima
Social networks have played a crucial role of information channels for understanding our daily lives beyond communication tools. In particular, their coupling with geographic location has boosted the worth of social media to detect, track, and predicate dynamic events and situations in the real world. While the amounts of geo-tagged social media are apparently increasing at every moment, we have few framework to handle spatiotemporal changes and analyze their relationships. In this paper, we propose a framework to understand dynamic social phenomena from the mountains of fragmented, noisy data flooding social media. First, we design a data model to describe morphological features of the populations of geo-location of social media and define a set of relationships by using differential measurements in spatial, temporal, and semantic dimensions. Then, we describe our real-time framework to extract morphometric features from streaming tweets, create the topological relationships, and store all features into a graph-based database. In the experiments, we show case studies related to two typhoons (Neoguri and Halong) and a landslide disaster (Hiroshima) with real tweet-sets in a visualization way.
{"title":"Sophy: a morphological framework for structuring geo-referenced social media","authors":"Kyoung-Sook Kim, Hirotaka Ogawa, Akihito Nakamura, I. Kojima","doi":"10.1145/2755492.2755498","DOIUrl":"https://doi.org/10.1145/2755492.2755498","url":null,"abstract":"Social networks have played a crucial role of information channels for understanding our daily lives beyond communication tools. In particular, their coupling with geographic location has boosted the worth of social media to detect, track, and predicate dynamic events and situations in the real world. While the amounts of geo-tagged social media are apparently increasing at every moment, we have few framework to handle spatiotemporal changes and analyze their relationships. In this paper, we propose a framework to understand dynamic social phenomena from the mountains of fragmented, noisy data flooding social media. First, we design a data model to describe morphological features of the populations of geo-location of social media and define a set of relationships by using differential measurements in spatial, temporal, and semantic dimensions. Then, we describe our real-time framework to extract morphometric features from streaming tweets, create the topological relationships, and store all features into a graph-based database. In the experiments, we show case studies related to two typhoons (Neoguri and Halong) and a landslide disaster (Hiroshima) with real tweet-sets in a visualization way.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123727484","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}
Long T. Le, Tina Eliassi-Rad, F. Provost, Lauren Moores
To conduct a successful targeting campaign in mobile advertising, one needs to have reliable location information from real-time bid requests. However, many real-time bid requests do not include fine-grained location information (such as latitude and longitude) because (1) the device or the application did not collect that information or (2) some components of the real-time bid ecosystem did not forward that information. In this paper, we present a three-step approach that takes as input hashed public IP addresses in real-time bid requests and (1) creates a weighted heterogenous network, (2) applies network-inference techniques to infer fine-grain (but possibly noisy) location information for the hashed public IPs, and (3) uses k-nearest neighbor and census data to assign census block group IDs to those hashed public IPs. Our experiments on two large real-world datasets show the accuracy of our approach to be over 74% for hashed IPs (regardless of their type: mobile or non-mobile) when basing the inference on only hashed public mobile IPs. This is notable since our inference is over 212K possibilities.
{"title":"Hyperlocal: inferring location of IP addresses in real-time bid requests for mobile ads","authors":"Long T. Le, Tina Eliassi-Rad, F. Provost, Lauren Moores","doi":"10.1145/2536689.2536807","DOIUrl":"https://doi.org/10.1145/2536689.2536807","url":null,"abstract":"To conduct a successful targeting campaign in mobile advertising, one needs to have reliable location information from real-time bid requests. However, many real-time bid requests do not include fine-grained location information (such as latitude and longitude) because (1) the device or the application did not collect that information or (2) some components of the real-time bid ecosystem did not forward that information. In this paper, we present a three-step approach that takes as input hashed public IP addresses in real-time bid requests and (1) creates a weighted heterogenous network, (2) applies network-inference techniques to infer fine-grain (but possibly noisy) location information for the hashed public IPs, and (3) uses k-nearest neighbor and census data to assign census block group IDs to those hashed public IPs. Our experiments on two large real-world datasets show the accuracy of our approach to be over 74% for hashed IPs (regardless of their type: mobile or non-mobile) when basing the inference on only hashed public mobile IPs. This is notable since our inference is over 212K possibilities.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129359054","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}
Relations between the dimension of social tie strength and the dimension of value of communicated information have been investigated in the past by researchers such as Mark Granovetter. Also the connection between spatial distance and the existence of ties in social networks with small world characteristics has been discussed by Liben-Nowell and others. In this contribution we aim at investigating the relation between the dimensions spatial distance and non-binary, continuous value of information. Furthermore, we discuss the connection between non-binary, continuous measures for value of information and the dimension of non-binary social, continuous measures of tie strength. We also especially investigate the interrelation between all three dimensions in Social Networking and especially the research question of whether a spatial dependency of the inverse relation between social tie strength and value of information exists which may be named 'Geo-Granovetter effect'. As a basis for our empirical investigations we used a large Twitter dataset, because this Social Medium allows us to simultaneously access spatial, social and informational dimensions of interaction and thus to simultaneously model these three dimensions for Social Networking. We found that the social tie strength decreases as expected with increasing spatial distance among participants in our data-set. We also observed that in general the information value decreases when the tie strength increases and that the value of information is independent from the distance. According to our findings, Social Media such as Twitter don't exhibit a Geo-Granovetter effect.
{"title":"Geographic aspects of tie strength and value of information in social networking","authors":"Georg Groh, Florian Straub, J. Eicher, David Grob","doi":"10.1145/2536689.2536803","DOIUrl":"https://doi.org/10.1145/2536689.2536803","url":null,"abstract":"Relations between the dimension of social tie strength and the dimension of value of communicated information have been investigated in the past by researchers such as Mark Granovetter. Also the connection between spatial distance and the existence of ties in social networks with small world characteristics has been discussed by Liben-Nowell and others. In this contribution we aim at investigating the relation between the dimensions spatial distance and non-binary, continuous value of information. Furthermore, we discuss the connection between non-binary, continuous measures for value of information and the dimension of non-binary social, continuous measures of tie strength. We also especially investigate the interrelation between all three dimensions in Social Networking and especially the research question of whether a spatial dependency of the inverse relation between social tie strength and value of information exists which may be named 'Geo-Granovetter effect'. As a basis for our empirical investigations we used a large Twitter dataset, because this Social Medium allows us to simultaneously access spatial, social and informational dimensions of interaction and thus to simultaneously model these three dimensions for Social Networking.\u0000 We found that the social tie strength decreases as expected with increasing spatial distance among participants in our data-set. We also observed that in general the information value decreases when the tie strength increases and that the value of information is independent from the distance. According to our findings, Social Media such as Twitter don't exhibit a Geo-Granovetter effect.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114395697","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 the current technological era the value of information sharing has emerged enormously while the contemporary phenomenon of Social Networking (SN) has provided an avenue for sharing information. The ubiquitous nature of SN services has focused mainly on "Who", "What" and "When", while the "Where" dimension has mainly been neglected. Only recently after realizing that "Where" dimension of information is present in almost 80% of any raw data, the SN platforms have started utilizing the location based information. This has led to the emergence of a new field, namely Location Based Social Networking (LBSN). A comprehensive literature review of LBSN reveals several shortcomings in both, the research and industrial implementation. One of the primary weaknesses is that the location in LBSN is being assumed and treated just as an auxiliary part of information (post, pictures, videos etc.) and not as a core element. This treatment undermines the true significance of location based information in LBSN. To overcome this limitation, current paper proposes an object based conceptual framework in which location reforms itself from a mere non-compulsory attribute of information to a completely new form i.e. an object. The location as an object will have its own attributes and associated behaviors. When this new location based information object is integrated into a LBSN platform, the interactions between location and human objects instigates, which resultantly exhibits new aspects of social and spatial communication not witnessed previously in the LBSN.
{"title":"An object based conceptual framework for location based social networking","authors":"Muhammad Haris, S. W. Jaffry","doi":"10.1145/2536689.2536809","DOIUrl":"https://doi.org/10.1145/2536689.2536809","url":null,"abstract":"In the current technological era the value of information sharing has emerged enormously while the contemporary phenomenon of Social Networking (SN) has provided an avenue for sharing information. The ubiquitous nature of SN services has focused mainly on \"Who\", \"What\" and \"When\", while the \"Where\" dimension has mainly been neglected. Only recently after realizing that \"Where\" dimension of information is present in almost 80% of any raw data, the SN platforms have started utilizing the location based information. This has led to the emergence of a new field, namely Location Based Social Networking (LBSN). A comprehensive literature review of LBSN reveals several shortcomings in both, the research and industrial implementation. One of the primary weaknesses is that the location in LBSN is being assumed and treated just as an auxiliary part of information (post, pictures, videos etc.) and not as a core element. This treatment undermines the true significance of location based information in LBSN. To overcome this limitation, current paper proposes an object based conceptual framework in which location reforms itself from a mere non-compulsory attribute of information to a completely new form i.e. an object. The location as an object will have its own attributes and associated behaviors. When this new location based information object is integrated into a LBSN platform, the interactions between location and human objects instigates, which resultantly exhibits new aspects of social and spatial communication not witnessed previously in the LBSN.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"584 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123170986","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}
TwitterStand is a novel way to track the news cycle by allowing people to view and browse the news with a map query interface. TF-IDF scores for each document that is linked to by a tweet (also termed twanchor [22] when the document is a news article) are calculated after they enter the system and pass initial classification filters. These scores are used to cluster similar tweets. Clusters must contain tweets from reputable sources in order for the clusters to form. These reputable sources are known as seeders as they essentially seed a cluster. Seeders have become an integral part of the TwitterStand architecture. An optimal system monitors the set of seeders in order to find newsworthy tweets quickly. This paper proposes methods to improve the current list of seeders by augmenting the pool with previously undiscovered users while routinely eliminating those that do not bring any value. We consider a successful seeder one who is timely in the reporting of large newsworthy events. An analysis of the current seeders precedes a proposed approach and serves as the basis for quantifying future seeder churn. A qualitative analysis based on that approach is conducted in an effort to quantitatively evaluate the process.
{"title":"Seeder finder: identifying additional needles in the Twitter haystack","authors":"Nick Gramsky, H. Samet","doi":"10.1145/2536689.2536808","DOIUrl":"https://doi.org/10.1145/2536689.2536808","url":null,"abstract":"TwitterStand is a novel way to track the news cycle by allowing people to view and browse the news with a map query interface. TF-IDF scores for each document that is linked to by a tweet (also termed twanchor [22] when the document is a news article) are calculated after they enter the system and pass initial classification filters. These scores are used to cluster similar tweets. Clusters must contain tweets from reputable sources in order for the clusters to form. These reputable sources are known as seeders as they essentially seed a cluster. Seeders have become an integral part of the TwitterStand architecture. An optimal system monitors the set of seeders in order to find newsworthy tweets quickly.\u0000 This paper proposes methods to improve the current list of seeders by augmenting the pool with previously undiscovered users while routinely eliminating those that do not bring any value. We consider a successful seeder one who is timely in the reporting of large newsworthy events. An analysis of the current seeders precedes a proposed approach and serves as the basis for quantifying future seeder churn. A qualitative analysis based on that approach is conducted in an effort to quantitatively evaluate the process.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132568977","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：