Improving user experience through personalized recommendations is crucial to organizing the abundance of data on news websites. Modeling user preferences based on implicit feedback has recently gained lots of attention, partly due to growing volume of web generated click stream data. Matrix factorization learned with stochastic gradient descent has successfully been adopted to approximate various ranking objectives. The aim of this paper is to test the performance of learning to rank approaches on the real-world dataset and apply some simple heuristics to consider temporal dynamics present in news domain. Our model is based on WARP loss with changes to classic factorization model.
{"title":"Learning to rank for personalized news recommendation","authors":"Pavel Shashkin, N. Karpov","doi":"10.1145/3106426.3109432","DOIUrl":"https://doi.org/10.1145/3106426.3109432","url":null,"abstract":"Improving user experience through personalized recommendations is crucial to organizing the abundance of data on news websites. Modeling user preferences based on implicit feedback has recently gained lots of attention, partly due to growing volume of web generated click stream data. Matrix factorization learned with stochastic gradient descent has successfully been adopted to approximate various ranking objectives. The aim of this paper is to test the performance of learning to rank approaches on the real-world dataset and apply some simple heuristics to consider temporal dynamics present in news domain. Our model is based on WARP loss with changes to classic factorization model.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77606566","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}
Jingjing Tang, Ying-jie Tian, Guoqiang Wu, Dewei Li
In recent years, nonparallel support vector machine (NPSVM) is proposed as a nonparallel hyperplane classifier with superior performance than standard SVM and existing nonparallel classifiers such as the twin support vector machine (TWSVM). With the perfect theoretical underpinnings and great practical success, NPSVM has been used to dealing with the classification tasks on different scales. Tackling large-scale classification problem is a challenge yet significant work. Although large-scale linear NPSVM model has already been efficiently solved by the dual coordinate descent (DCD) algorithm or alternating direction method of multipliers (ADMM), we present a new strategy to solve the primal form of linear NPSVM different from existing work in this paper. Our algorithm is designed in the framework of the stochastic gradient descent (SGD), which is well suited to large-scale problem. Experiments are conducted on five large-scale data sets to confirm the effectiveness of our method.
{"title":"Stochastic gradient descent for large-scale linear nonparallel SVM","authors":"Jingjing Tang, Ying-jie Tian, Guoqiang Wu, Dewei Li","doi":"10.1145/3106426.3109427","DOIUrl":"https://doi.org/10.1145/3106426.3109427","url":null,"abstract":"In recent years, nonparallel support vector machine (NPSVM) is proposed as a nonparallel hyperplane classifier with superior performance than standard SVM and existing nonparallel classifiers such as the twin support vector machine (TWSVM). With the perfect theoretical underpinnings and great practical success, NPSVM has been used to dealing with the classification tasks on different scales. Tackling large-scale classification problem is a challenge yet significant work. Although large-scale linear NPSVM model has already been efficiently solved by the dual coordinate descent (DCD) algorithm or alternating direction method of multipliers (ADMM), we present a new strategy to solve the primal form of linear NPSVM different from existing work in this paper. Our algorithm is designed in the framework of the stochastic gradient descent (SGD), which is well suited to large-scale problem. Experiments are conducted on five large-scale data sets to confirm the effectiveness of our method.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77630169","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}
Emotions have a significant impact on the purchasing process. Due to novel affective computing approaches, affective information of users can be acquired in implicit and therefore non-intrusive manner. Recent research in the field of recommender systems indicates that the incorporation of affective user information in the prediction model has a positive impact on the recommender systems accuracy. Existing research mainly focused on product recommendations in the movie anfd music domain. Our paper investigates the impact of affective emotions on fashion products, which is one of the largest consumer industries. We integrate the users' mood and their emotion in the prediction model, and the results are compared to the baseline model using rating data only. For this, we generate a dataset with 337 participants, 64 products, and 10816 ratings. We determine the mood information using the PANAS questionnaire, and the emotion by using the SAM self-assessment method. The affective information is integrated leveraging Factorization Machines. The evaluation of the offline experiments reveals that in new item cold-start scenarios the mood information has a positive impact on the prediction accuracy, whereas the emotion information has a negative impact.
{"title":"Emotions and fashion recommendations: evaluating the predictive power of affective information for the prediction of fashion product preferences in cold-start scenarios","authors":"Alexander Piazza, Pavlina Kröckel, F. Bodendorf","doi":"10.1145/3106426.3109441","DOIUrl":"https://doi.org/10.1145/3106426.3109441","url":null,"abstract":"Emotions have a significant impact on the purchasing process. Due to novel affective computing approaches, affective information of users can be acquired in implicit and therefore non-intrusive manner. Recent research in the field of recommender systems indicates that the incorporation of affective user information in the prediction model has a positive impact on the recommender systems accuracy. Existing research mainly focused on product recommendations in the movie anfd music domain. Our paper investigates the impact of affective emotions on fashion products, which is one of the largest consumer industries. We integrate the users' mood and their emotion in the prediction model, and the results are compared to the baseline model using rating data only. For this, we generate a dataset with 337 participants, 64 products, and 10816 ratings. We determine the mood information using the PANAS questionnaire, and the emotion by using the SAM self-assessment method. The affective information is integrated leveraging Factorization Machines. The evaluation of the offline experiments reveals that in new item cold-start scenarios the mood information has a positive impact on the prediction accuracy, whereas the emotion information has a negative impact.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74356836","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}
Mehdi Rajabi Asadabadi, Morteza Saberi, Elizabeth Chang
Avoiding ambiguity and fuzziness in the determination of the requirements is a crucial factor in the success of Performance Based Contracting (PBC). To date, there is a research gap because insufficient studies have been undertaken to address this significant issue in the pro-curement process. Previous studies that have been con-ducted on requirement specification and elicitation are limited to software engineering. This study investigates this issue in the procurement process and proposes an integrated framework using Natural Language Pro-cessing (NLP), game theory and fuzzy logic. This re-search contributes to contract theory by opening a new line of research which paves the way for leveraging arti-ficial intelligence techniques in automated or semi-automated contract monitoring.
{"title":"A fuzzy game based framework to address ambiguities in performance based contracting","authors":"Mehdi Rajabi Asadabadi, Morteza Saberi, Elizabeth Chang","doi":"10.1145/3106426.3110323","DOIUrl":"https://doi.org/10.1145/3106426.3110323","url":null,"abstract":"Avoiding ambiguity and fuzziness in the determination of the requirements is a crucial factor in the success of Performance Based Contracting (PBC). To date, there is a research gap because insufficient studies have been undertaken to address this significant issue in the pro-curement process. Previous studies that have been con-ducted on requirement specification and elicitation are limited to software engineering. This study investigates this issue in the procurement process and proposes an integrated framework using Natural Language Pro-cessing (NLP), game theory and fuzzy logic. This re-search contributes to contract theory by opening a new line of research which paves the way for leveraging arti-ficial intelligence techniques in automated or semi-automated contract monitoring.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74898580","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}
D. Martins, G. Vossen, Fernando Buarque de Lima-Neto
The Big Data era is affording a paradigm change on decision-making approaches. More and more, companies as well as individuals are relying on data rather than on the so called "gut feeling" to make decisions. However, searching the Web for carrying out purchases is not completely satisfactory yet, given the arduousness of finding suitable quality data. This has contributed to the emergence of data marketplaces as an alternative to traditional data commerce, as they provide appropriate online environments for data offering and purchasing. Nevertheless, as the number of available datasets to purchase increases, the task of buying appropriate offers is, very often, challenging. In this sense, we propose an intelligent decision support system to help buyers in purchasing data offers based on a multiple-criteria decision analysis. Experimental results show that our approach provides an interactive way that addresses buyers' needs, allowing them to state and easily refine their preferences, without any specific order, via a series of dataset recommendations.
{"title":"Intelligent decision support for data purchase","authors":"D. Martins, G. Vossen, Fernando Buarque de Lima-Neto","doi":"10.1145/3106426.3106434","DOIUrl":"https://doi.org/10.1145/3106426.3106434","url":null,"abstract":"The Big Data era is affording a paradigm change on decision-making approaches. More and more, companies as well as individuals are relying on data rather than on the so called \"gut feeling\" to make decisions. However, searching the Web for carrying out purchases is not completely satisfactory yet, given the arduousness of finding suitable quality data. This has contributed to the emergence of data marketplaces as an alternative to traditional data commerce, as they provide appropriate online environments for data offering and purchasing. Nevertheless, as the number of available datasets to purchase increases, the task of buying appropriate offers is, very often, challenging. In this sense, we propose an intelligent decision support system to help buyers in purchasing data offers based on a multiple-criteria decision analysis. Experimental results show that our approach provides an interactive way that addresses buyers' needs, allowing them to state and easily refine their preferences, without any specific order, via a series of dataset recommendations.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80130359","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}
An objective assessment of collaborative filtering techniques and recommender systems requires application of suitable predictive accuracy metrics. In real life, individuals meet their decisions with considerable uncertainty. This raises the question to what extent the comparison between observed and predicted user responses can be seen as an evident proof of systematic quality differences. In this paper, we accordingly justify underlying assumptions of quality assessment, introduce an appropriate uncertainty-aware evaluation strategy for recommender comparisons, and demonstrate its feasibility and consistency in experiments with real users.
{"title":"Comparative assessment of rating prediction techniques under response uncertainty","authors":"Sergej Sizov","doi":"10.1145/3106426.3106506","DOIUrl":"https://doi.org/10.1145/3106426.3106506","url":null,"abstract":"An objective assessment of collaborative filtering techniques and recommender systems requires application of suitable predictive accuracy metrics. In real life, individuals meet their decisions with considerable uncertainty. This raises the question to what extent the comparison between observed and predicted user responses can be seen as an evident proof of systematic quality differences. In this paper, we accordingly justify underlying assumptions of quality assessment, introduce an appropriate uncertainty-aware evaluation strategy for recommender comparisons, and demonstrate its feasibility and consistency in experiments with real users.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83727890","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, to resolve some issues on personal assistance that are working on some social network services, we present a platform that allows agents to analyze some associated informations to make effective protraction and prevention of cyber-bullying. We also present a prototype implementation of our platform that allows agents handle and analyze contexts on the Mastodon-based social networks. On the current implementation, a personal assistant agent can run on a same browser that opened web site of the social networking service.
{"title":"MstdnDeck: an agent-based protection of cyber-bullying on distributedly managed linked microbloggings","authors":"Sho Oishi, Naoki Fukuta","doi":"10.1145/3106426.3109415","DOIUrl":"https://doi.org/10.1145/3106426.3109415","url":null,"abstract":"In this paper, to resolve some issues on personal assistance that are working on some social network services, we present a platform that allows agents to analyze some associated informations to make effective protraction and prevention of cyber-bullying. We also present a prototype implementation of our platform that allows agents handle and analyze contexts on the Mastodon-based social networks. On the current implementation, a personal assistant agent can run on a same browser that opened web site of the social networking service.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83275752","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}
Information radiators are ubiquitous stationary installations that radiate information that is likely to improve awareness of passers-by in semi-public environments like organization floors. In this paper, we present the idea of using several kinds of information radiators for enhancing urban participation of seniors - by providing awareness for supporting the planning and execution of activities in public environments. We motivate the idea and discuss interaction design as well as HCI challenges to be addressed in future work.1
{"title":"Information radiators: using large screens and small devices to support awareness in urban space","authors":"Michael Koch, Anna Kötteritzsch, Julian Fietkau","doi":"10.1145/3106426.3109039","DOIUrl":"https://doi.org/10.1145/3106426.3109039","url":null,"abstract":"Information radiators are ubiquitous stationary installations that radiate information that is likely to improve awareness of passers-by in semi-public environments like organization floors. In this paper, we present the idea of using several kinds of information radiators for enhancing urban participation of seniors - by providing awareness for supporting the planning and execution of activities in public environments. We motivate the idea and discuss interaction design as well as HCI challenges to be addressed in future work.1","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77663745","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}
Supporting heterogeneous ontologies is an important issue on retrieving from and linking to linked data stored in various SPARQL endpoints via SPARQL queries. There are several approaches to support the coding process of a SPARQL query for users who are unfamiliar to code it. On the use of some ontology mapping-based support approaches on SPARQL-based query systems, we often assume that the users already have appropriate weighted ontology mappings for the ontologies used in the query. In this paper, we present ontology mapping inspection mechanisms for mapping-enhanced SPARQL queries to widely retrieve various data from Linked Open Data (LOD). Our dynamic ontology mapping adaptation technique complements the used incomplete ontology mappings by dynamically detecting and adding missing mappings to include the correspondences between entities of terms in heterogeneous ontologies.
{"title":"A mapping-enhanced linked data inspection and querying support system using dynamic ontology matching","authors":"Takuya Adachi, Naoki Fukuta","doi":"10.1145/3106426.3109414","DOIUrl":"https://doi.org/10.1145/3106426.3109414","url":null,"abstract":"Supporting heterogeneous ontologies is an important issue on retrieving from and linking to linked data stored in various SPARQL endpoints via SPARQL queries. There are several approaches to support the coding process of a SPARQL query for users who are unfamiliar to code it. On the use of some ontology mapping-based support approaches on SPARQL-based query systems, we often assume that the users already have appropriate weighted ontology mappings for the ontologies used in the query. In this paper, we present ontology mapping inspection mechanisms for mapping-enhanced SPARQL queries to widely retrieve various data from Linked Open Data (LOD). Our dynamic ontology mapping adaptation technique complements the used incomplete ontology mappings by dynamically detecting and adding missing mappings to include the correspondences between entities of terms in heterogeneous ontologies.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90755755","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}
Alex Hernández-García, F. Martínez, F. Díaz-de-María
This paper contributes to the field of affective video content analysis through the novel employment of electrodermal activity (EDA) measurements as ground truth for machine learning algorithms. The variation of the electrical properties of the skin, known as EDA, is a psychophysiological indicator widely used in medicine, psychology and neuroscience which can be considered a somatic marker of the emotional and attentional reaction of subjects towards stimuli. One of its main advantages is that the recorded information is not biased by the cognitive process of giving an opinion or a score to characterize the subjective perception. In this work, we predict the levels of emotion and attention, derived from EDA records, by means of a small set of low-level visual descriptors computed from the video stimuli. Linear regression experiments show that our descriptors predict significantly well the sum of emotion and attention levels, reaching a coefficient of determination R2 = 0.25. This result sets a promising path for further research on the prediction of emotion and attention from videos using EDA.
{"title":"Emotion and attention: predicting electrodermal activity through video visual descriptors","authors":"Alex Hernández-García, F. Martínez, F. Díaz-de-María","doi":"10.1145/3106426.3109418","DOIUrl":"https://doi.org/10.1145/3106426.3109418","url":null,"abstract":"This paper contributes to the field of affective video content analysis through the novel employment of electrodermal activity (EDA) measurements as ground truth for machine learning algorithms. The variation of the electrical properties of the skin, known as EDA, is a psychophysiological indicator widely used in medicine, psychology and neuroscience which can be considered a somatic marker of the emotional and attentional reaction of subjects towards stimuli. One of its main advantages is that the recorded information is not biased by the cognitive process of giving an opinion or a score to characterize the subjective perception. In this work, we predict the levels of emotion and attention, derived from EDA records, by means of a small set of low-level visual descriptors computed from the video stimuli. Linear regression experiments show that our descriptors predict significantly well the sum of emotion and attention levels, reaching a coefficient of determination R2 = 0.25. This result sets a promising path for further research on the prediction of emotion and attention from videos using EDA.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78417325","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：