In the Internet of Things era, we need to face increased masses of data, across all domains. Current researches have long been working to develop methods that help users to identify, extract, visualize and understand useful information from these huge masses of high dimensional and often weakly structured and/or non-standardized data. Our goal is to propose a solution for supporting users to interactively analyze such data flow and to visualize their most relevant parts through proper interaction style, without getting overwhelmed. In the paper, we describe a multi-level recommendation system (RS) by providing users with a decisionmaking process interactively accessible and by integrating it with social and crowdsourcing analysis, and interpretations that can lead to a new and meaningful use and presentation of data. to provide users with a decision-making process interactively accessible and enriched with social and crowdsourcing analysis tools, and interpretations that can lead to a new and meaningful use and presentation of data. The challenge is to enable effective human control over powerful machine algorithms based on a set of recommendation services used to filter data and choose proper data visualization and interaction style for supporting user’s insight, discoveries and decision making.
User-centered recommendation services in Internet of things Era / S. Valtolina, M. Mesiti, B.R. Barricelli. ((Intervento presentato al convegno Cultures of Participation in the Digital Age : Social Computing for Working, Learning, and Living tenutosi a Como nel 2014.
User-centered recommendation services in Internet of things Era
S. ValtolinaPrimo
;M. MesitiSecondo
;B.R. BarricelliUltimo
2014
Abstract
In the Internet of Things era, we need to face increased masses of data, across all domains. Current researches have long been working to develop methods that help users to identify, extract, visualize and understand useful information from these huge masses of high dimensional and often weakly structured and/or non-standardized data. Our goal is to propose a solution for supporting users to interactively analyze such data flow and to visualize their most relevant parts through proper interaction style, without getting overwhelmed. In the paper, we describe a multi-level recommendation system (RS) by providing users with a decisionmaking process interactively accessible and by integrating it with social and crowdsourcing analysis, and interpretations that can lead to a new and meaningful use and presentation of data. to provide users with a decision-making process interactively accessible and enriched with social and crowdsourcing analysis tools, and interpretations that can lead to a new and meaningful use and presentation of data. The challenge is to enable effective human control over powerful machine algorithms based on a set of recommendation services used to filter data and choose proper data visualization and interaction style for supporting user’s insight, discoveries and decision making.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.