Pub Date : 2017-07-09DOI: 10.1109/SMAP.2017.8022662
Zuzana Kucharikova, Jakub Simko
Nowadays, many cities and communes suffer from advertisements appearing on aesthetically inappropriate or illegal places. This contamination of public space is called visual pollution. The first step in the fight against visual pollution is localization of physical advertising media (e.g., billboards) as accurately as is possible. One of the ways is to use volunteer effort through outdoor crowdsourcing. Smart mobile devices can support this process through localization sensors. However, these sensors are inaccurate enough on their own, plus, the media are not located exactly where the volunteers capture them. Therefore, the media localization is presently inaccurate. This paper presents a work-in-progress method to improve the localization of physical advertisement media. As input, the method takes captured media images along with spatial information about the device. The images are then clustered based on their locations, to form sets corresponding to the true physical media. Then, using visual analysis of the images and spatial orientation of devices, the method computes expected location of the physical media.
{"title":"Visual pollution localization through crowdsourcing and visual similarity clustering","authors":"Zuzana Kucharikova, Jakub Simko","doi":"10.1109/SMAP.2017.8022662","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022662","url":null,"abstract":"Nowadays, many cities and communes suffer from advertisements appearing on aesthetically inappropriate or illegal places. This contamination of public space is called visual pollution. The first step in the fight against visual pollution is localization of physical advertising media (e.g., billboards) as accurately as is possible. One of the ways is to use volunteer effort through outdoor crowdsourcing. Smart mobile devices can support this process through localization sensors. However, these sensors are inaccurate enough on their own, plus, the media are not located exactly where the volunteers capture them. Therefore, the media localization is presently inaccurate. This paper presents a work-in-progress method to improve the localization of physical advertisement media. As input, the method takes captured media images along with spatial information about the device. The images are then clustered based on their locations, to form sets corresponding to the true physical media. Then, using visual analysis of the images and spatial orientation of devices, the method computes expected location of the physical media.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125826023","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}
Pub Date : 2017-07-09DOI: 10.1109/SMAP.2017.8022661
Rastislav Krchnavy, Marián Simko
In this paper we tackle the issue of sentiment analysis of social network posts in a not well targeted language — Slovak. There is a significant lack of research in this area for minor languages, as they often introduce additional language-specific issues for text processing. In case of Slovak, common issues are high flection, complex morphology and syntax. User-generated content of social networks introduces additional challenges (variability of diacritics, inconsistent style, high error rate) that make the task even harder. In this paper, we propose a method for sentiment analysis of social network posts on Facebook. The proposed method is based on machine learning and incorporates multilevel text pre-processing aiming to deal with specifics of user-generated social content. The evaluation in a real-word setting employing data from Facebook pages of multiple well-known companies shows accuracy of our method comparable with approaches for major world languages.
{"title":"Sentiment analysis of social network posts in Slovak language","authors":"Rastislav Krchnavy, Marián Simko","doi":"10.1109/SMAP.2017.8022661","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022661","url":null,"abstract":"In this paper we tackle the issue of sentiment analysis of social network posts in a not well targeted language — Slovak. There is a significant lack of research in this area for minor languages, as they often introduce additional language-specific issues for text processing. In case of Slovak, common issues are high flection, complex morphology and syntax. User-generated content of social networks introduces additional challenges (variability of diacritics, inconsistent style, high error rate) that make the task even harder. In this paper, we propose a method for sentiment analysis of social network posts on Facebook. The proposed method is based on machine learning and incorporates multilevel text pre-processing aiming to deal with specifics of user-generated social content. The evaluation in a real-word setting employing data from Facebook pages of multiple well-known companies shows accuracy of our method comparable with approaches for major world languages.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129103871","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}
Pub Date : 2017-07-09DOI: 10.1109/SMAP.2017.8022671
Justus Schwan, E. Ghaleb, E. Hortal, S. Asteriadis
Deep learning is used for all kinds of tasks which require human-like performance, such as voice and image recognition in smartphones, smart home technology, and self-driving cars. While great advances have been made in the field, results are often not satisfactory when compared to human performance. In the field of facial emotion recognition, especially in the wild, Convolutional Neural Networks (CNN) are employed because of their excellent generalization properties. However, while CNNs can learn a representation for certain object classes, an amount of (annotated) training data roughly proportional to the class's complexity is needed and seldom available. This work describes an advanced pre-processing algorithm for facial images and a transfer learning mechanism, two potential candidates for relaxing this requirement. Using these algorithms, a lightweight face emotion recognition application for Human-Computer Interaction with TurtleBot units was developed.
{"title":"High-performance and lightweight real-time deep face emotion recognition","authors":"Justus Schwan, E. Ghaleb, E. Hortal, S. Asteriadis","doi":"10.1109/SMAP.2017.8022671","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022671","url":null,"abstract":"Deep learning is used for all kinds of tasks which require human-like performance, such as voice and image recognition in smartphones, smart home technology, and self-driving cars. While great advances have been made in the field, results are often not satisfactory when compared to human performance. In the field of facial emotion recognition, especially in the wild, Convolutional Neural Networks (CNN) are employed because of their excellent generalization properties. However, while CNNs can learn a representation for certain object classes, an amount of (annotated) training data roughly proportional to the class's complexity is needed and seldom available. This work describes an advanced pre-processing algorithm for facial images and a transfer learning mechanism, two potential candidates for relaxing this requirement. Using these algorithms, a lightweight face emotion recognition application for Human-Computer Interaction with TurtleBot units was developed.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121246915","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}
Pub Date : 2017-07-09DOI: 10.1109/SMAP.2017.8022660
Michalis Korakakis, E. Spyrou, Phivos Mylonas
This short survey paper attempts to provide an overview of the most recent research works on the popular politics domain within the framework of the Twitter social network. Given both the political turmoil that arouse at the end of 2016 and early 2017, and the increasing popularity of social networks in general, and Twitter, in particular, we feel that this topic forms an attractive candidate for fellow data mining researchers that came into sight over the last few months. Herein, we start by presenting a brief overview of our motivation and continue with basic information on the Twitter platform, which constitutes two clearly identifiable components, namely as an online news source and as one of the most popular social networking sites. Focus is then given to research works dealing with sentiment analysis in political topics and opinion polls, whereas we continue by reviewing the Twittersphere from the computational social science point of view, by including behavior analysis, social interaction and social influence identification methods and by discerning and discriminating its useful types within the social network, thus envisioning possible further utilization scenarios for the collected information. A short discussion on the identified conclusions and a couple of future research directions concludes the survey.
{"title":"A survey on political event analysis in Twitter","authors":"Michalis Korakakis, E. Spyrou, Phivos Mylonas","doi":"10.1109/SMAP.2017.8022660","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022660","url":null,"abstract":"This short survey paper attempts to provide an overview of the most recent research works on the popular politics domain within the framework of the Twitter social network. Given both the political turmoil that arouse at the end of 2016 and early 2017, and the increasing popularity of social networks in general, and Twitter, in particular, we feel that this topic forms an attractive candidate for fellow data mining researchers that came into sight over the last few months. Herein, we start by presenting a brief overview of our motivation and continue with basic information on the Twitter platform, which constitutes two clearly identifiable components, namely as an online news source and as one of the most popular social networking sites. Focus is then given to research works dealing with sentiment analysis in political topics and opinion polls, whereas we continue by reviewing the Twittersphere from the computational social science point of view, by including behavior analysis, social interaction and social influence identification methods and by discerning and discriminating its useful types within the social network, thus envisioning possible further utilization scenarios for the collected information. A short discussion on the identified conclusions and a couple of future research directions concludes the survey.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128192876","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}
Pub Date : 2017-07-09DOI: 10.1109/SMAP.2017.8022659
Karen S. Jung, O. Tonguz
Social networking sites not only have billions of users but detailed content about each individual's daily life. This detailed information about a person's life could be exploited to allow individuals to learn more about themselves. In this paper, we introduce the concept of using social networks to foresee changes in an individual's health. We develop a new model that can predict if a person has recently undergone weight loss by analyzing the text from the person's tweets. Sentiment analysis, parts-of-speech (POS) tagging, and categorization are used in this model. The model is tested on Twitter users and a good statistical accuracy is observed. The success of this model suggests that this idea could be further explored to identify other patterns and create new models for a variety of health changes and health problems, particularly those that are of huge interest to individuals and businesses.
{"title":"Using social networks to predict changes in health: Extended abstract","authors":"Karen S. Jung, O. Tonguz","doi":"10.1109/SMAP.2017.8022659","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022659","url":null,"abstract":"Social networking sites not only have billions of users but detailed content about each individual's daily life. This detailed information about a person's life could be exploited to allow individuals to learn more about themselves. In this paper, we introduce the concept of using social networks to foresee changes in an individual's health. We develop a new model that can predict if a person has recently undergone weight loss by analyzing the text from the person's tweets. Sentiment analysis, parts-of-speech (POS) tagging, and categorization are used in this model. The model is tested on Twitter users and a good statistical accuracy is observed. The success of this model suggests that this idea could be further explored to identify other patterns and create new models for a variety of health changes and health problems, particularly those that are of huge interest to individuals and businesses.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131933617","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}
Pub Date : 2017-07-09DOI: 10.1109/SMAP.2017.8022664
Róbert Móro, Patrik Berger, M. Bieliková
Electroencefalography (EEG) has a wide range of applications in human-computer interaction and in adaptation and personalization of the interfaces. It can be used either as a sensor, e.g., for emotion detection, or as an input device that allows to take actions based on the brain's response to the presented stimuli. For the latter, it is crucial to be able to reliably detect event-related potentials (ERPs), which can be a hard task because of the noise in the signal, especially when using affordable consumer-oriented devices, such as Emotiv Epoc. In the paper, we present a method of EEG signal processing and classification for detection of ERP P300 wave. We particularly focus on the adaptive channel selection and propose to use genetic algorithm combined with linear discriminant analysis to determine the optimal subset of electrodes for signal processing for each individual user. We evaluated our proposed method on a standard data set outperforming the existing approaches even with decreasing size of a training set. In addition, we conducted a user study with Emotiv Epoc device on a standard P300 Speller task in order to compare the results of our method and to find out, whether this device is suitable for P300 detection.
{"title":"Towards adaptive brain-computer interfaces: Improving accuracy of detection of event-related potentials","authors":"Róbert Móro, Patrik Berger, M. Bieliková","doi":"10.1109/SMAP.2017.8022664","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022664","url":null,"abstract":"Electroencefalography (EEG) has a wide range of applications in human-computer interaction and in adaptation and personalization of the interfaces. It can be used either as a sensor, e.g., for emotion detection, or as an input device that allows to take actions based on the brain's response to the presented stimuli. For the latter, it is crucial to be able to reliably detect event-related potentials (ERPs), which can be a hard task because of the noise in the signal, especially when using affordable consumer-oriented devices, such as Emotiv Epoc. In the paper, we present a method of EEG signal processing and classification for detection of ERP P300 wave. We particularly focus on the adaptive channel selection and propose to use genetic algorithm combined with linear discriminant analysis to determine the optimal subset of electrodes for signal processing for each individual user. We evaluated our proposed method on a standard data set outperforming the existing approaches even with decreasing size of a training set. In addition, we conducted a user study with Emotiv Epoc device on a standard P300 Speller task in order to compare the results of our method and to find out, whether this device is suitable for P300 detection.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116909698","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}
Pub Date : 2017-07-01DOI: 10.1109/SMAP.2017.8022667
N. Tsapatsoulis, Constantinos Djouvas
Sentiment analysis of Twitter data became a research trend the last decade. Thanks to the Twitter API, massive amounts of tweets, relating to a topic of interest, can be collected in real time. Performing sentiment analysis of these tweets can be used to conduct social sensing and opinion mining. For instance, forecasting elections is a primary area in which sentiment analysis of tweets has been extensively applied the last few years. Sentiment analysis of Twitter data presents important challenges compared to the similar task of text classification. Tweets are limited to 140 characters; thus, the conveyed message is compressed and often context-dependent. The tweets are informal and unstructured, usually lacking grammatical soundness and use of a standard lexicon. On the other hand, tweets are usually annotated by their authors regarding their topic and sentiment with the aid of hashtags and emoticons. Identifying appropriate features for sentiment analysis of tweets remains an open research area since text indexing methods face the sparseness problem while POS tagging methods fail due to the lack of grammatical structure of tweets. Character based features, i.e., n-grams of characters, are currently getting popular because they are language independent. However, their effectiveness remains quite low. In this paper, we argue that tokens used by humans for sentiment analysis of tweets are probably the best feature set one can use for that purpose. We compare several automatically extracted features with the features (tokens) used by humans for tweet classification, under a machine learning framework. The results show that the manually indicated tokens combined with a Decision Tree classifier outperform any other feature set-classification algorithm combination. The manually annotated dataset that was used in our experiments is publicly available for anyone who wishes to use it.
{"title":"Feature extraction for tweet classification: Do the humans perform better?","authors":"N. Tsapatsoulis, Constantinos Djouvas","doi":"10.1109/SMAP.2017.8022667","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022667","url":null,"abstract":"Sentiment analysis of Twitter data became a research trend the last decade. Thanks to the Twitter API, massive amounts of tweets, relating to a topic of interest, can be collected in real time. Performing sentiment analysis of these tweets can be used to conduct social sensing and opinion mining. For instance, forecasting elections is a primary area in which sentiment analysis of tweets has been extensively applied the last few years. Sentiment analysis of Twitter data presents important challenges compared to the similar task of text classification. Tweets are limited to 140 characters; thus, the conveyed message is compressed and often context-dependent. The tweets are informal and unstructured, usually lacking grammatical soundness and use of a standard lexicon. On the other hand, tweets are usually annotated by their authors regarding their topic and sentiment with the aid of hashtags and emoticons. Identifying appropriate features for sentiment analysis of tweets remains an open research area since text indexing methods face the sparseness problem while POS tagging methods fail due to the lack of grammatical structure of tweets. Character based features, i.e., n-grams of characters, are currently getting popular because they are language independent. However, their effectiveness remains quite low. In this paper, we argue that tokens used by humans for sentiment analysis of tweets are probably the best feature set one can use for that purpose. We compare several automatically extracted features with the features (tokens) used by humans for tweet classification, under a machine learning framework. The results show that the manually indicated tokens combined with a Decision Tree classifier outperform any other feature set-classification algorithm combination. The manually annotated dataset that was used in our experiments is publicly available for anyone who wishes to use it.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115414358","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}
Pub Date : 2017-07-01DOI: 10.1109/SMAP.2017.8022657
David Andresic, Petr Šaloun, Ioannis Anagnostopoulos
Apache Spark is commonly used as a big data analytical platform on powerful computer clusters, as it primarily employ the main computer memory for the evaluation. Our attempt adds self-organizing map software libraries onto a single big data analytical stack and is efficient and fast enough even on a standard single computer. This innovative approach brings the big data analysis to researchers with limited resources. Our genuine idea was experimentally confirmed and is described here. As a case study for our method we we used the available #Brexit data and the sentiment analysis of corresponding tweets and the correlation with the stock exchange data.
{"title":"Efficient big data analysis on a single machine using apache spark and self-organizing map libraries","authors":"David Andresic, Petr Šaloun, Ioannis Anagnostopoulos","doi":"10.1109/SMAP.2017.8022657","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022657","url":null,"abstract":"Apache Spark is commonly used as a big data analytical platform on powerful computer clusters, as it primarily employ the main computer memory for the evaluation. Our attempt adds self-organizing map software libraries onto a single big data analytical stack and is efficient and fast enough even on a standard single computer. This innovative approach brings the big data analysis to researchers with limited resources. Our genuine idea was experimentally confirmed and is described here. As a case study for our method we we used the available #Brexit data and the sentiment analysis of corresponding tweets and the correlation with the stock exchange data.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126139794","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}
Pub Date : 2017-07-01DOI: 10.1109/SMAP.2017.8022663
A. Metzmacher, V. Heinrichs, B. Falk, R. Schmitt
The research presented is the first working step towards the goal of developing a domain-independent method for sentiment analysis of German customer feedback in social media. The approach proposes to apply the concept of natural language processing (NLP) to customer language processing (CLP). In this context we hypothesize an indifference in annotator ability in assigning customer reviews of tangible vs. intangible goods and an indifferences within customers' writing styles within their evaluation of these goods. To test these hypotheses, a study was conducted where participants had to assign the sentiment as well as the subject of customer reviews and its evaluative attribute. The results reveal that the inter-rater reliability of annotators does not differ significantly with respect to product groups. However a slight difference with respect to product categories could be observed. Moreover, there occur variations within the inter-rater ability according to the emotional commitment towards products.
{"title":"Customer language processing: Extended abstract","authors":"A. Metzmacher, V. Heinrichs, B. Falk, R. Schmitt","doi":"10.1109/SMAP.2017.8022663","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022663","url":null,"abstract":"The research presented is the first working step towards the goal of developing a domain-independent method for sentiment analysis of German customer feedback in social media. The approach proposes to apply the concept of natural language processing (NLP) to customer language processing (CLP). In this context we hypothesize an indifference in annotator ability in assigning customer reviews of tangible vs. intangible goods and an indifferences within customers' writing styles within their evaluation of these goods. To test these hypotheses, a study was conducted where participants had to assign the sentiment as well as the subject of customer reviews and its evaluative attribute. The results reveal that the inter-rater reliability of annotators does not differ significantly with respect to product groups. However a slight difference with respect to product categories could be observed. Moreover, there occur variations within the inter-rater ability according to the emotional commitment towards products.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123801415","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}
Pub Date : 2017-07-01DOI: 10.1109/SMAP.2017.8022673
Ahmed Dahroug, Martín López Nores, J. Pazos-Arias, Silvia González-Soutelo, S. Reboreda-Morillo, Angeliki Antoniou
Cultural heritage is typically not on the people's top lists when searching for entertainment activities. Publicized temporary exhibitions can draw many visitors to a museum, urged by the opportunity of seeing certain items, but in general there are no particular stimuli and the visits are postponed once and again, if not forever. In this paper, we argue that it is possible to instigate curiosity in relation to dates, periods and events that are relevant to the potential visitors and connected to the cultural heritage items in direct or subtle ways. Likewise, proper reasoning about dates can improve the experiences of actual visitors, by promoting serendipitous learning, increasing retention and revealing that subsequent visits may drive them around the venue following new appealing narratives. We present the outline of a recommender system grounded on rich semantic modeling of relevant dates in the user profiles, in the cultural heritage knowledge bases and in an almanac of important days, connected to keywords and/or historical events and characters. We also explain how this system is going to be used in the pilot experiments of the CROSSCULT EU project, starting in September 2017.
{"title":"Exploiting relevant dates to promote serendipity and situational curiosity in cultural heritage experiences","authors":"Ahmed Dahroug, Martín López Nores, J. Pazos-Arias, Silvia González-Soutelo, S. Reboreda-Morillo, Angeliki Antoniou","doi":"10.1109/SMAP.2017.8022673","DOIUrl":"https://doi.org/10.1109/SMAP.2017.8022673","url":null,"abstract":"Cultural heritage is typically not on the people's top lists when searching for entertainment activities. Publicized temporary exhibitions can draw many visitors to a museum, urged by the opportunity of seeing certain items, but in general there are no particular stimuli and the visits are postponed once and again, if not forever. In this paper, we argue that it is possible to instigate curiosity in relation to dates, periods and events that are relevant to the potential visitors and connected to the cultural heritage items in direct or subtle ways. Likewise, proper reasoning about dates can improve the experiences of actual visitors, by promoting serendipitous learning, increasing retention and revealing that subsequent visits may drive them around the venue following new appealing narratives. We present the outline of a recommender system grounded on rich semantic modeling of relevant dates in the user profiles, in the cultural heritage knowledge bases and in an almanac of important days, connected to keywords and/or historical events and characters. We also explain how this system is going to be used in the pilot experiments of the CROSSCULT EU project, starting in September 2017.","PeriodicalId":441461,"journal":{"name":"2017 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125658561","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：