Search results for "proactive search"

showing 3 items of 3 documents

Entity Recommendation for Everyday Digital Tasks

2021

| openaire: EC/H2020/826266/EU//CO-ADAPT Recommender systems can support everyday digital tasks by retrieving and recommending useful information contextually. This is becoming increasingly relevant in services and operating systems. Previous research often focuses on specific recommendation tasks with data captured from interactions with an individual application. The quality of recommendations is also often evaluated addressing only computational measures of accuracy, without investigating the usefulness of recommendations in realistic tasks. The aim of this work is to synthesize the research in this area through a novel approach by (1) demonstrating comprehensive digital activity monitor…

ExploitSettore INF/01 - InformaticaINFORMATIONComputer sciencemedia_common.quotation_subjectRelevance feedbackContext (language use)02 engineering and technologyTransparency (human–computer interaction)Recommender system113 Computer and information sciencesData scienceHuman-Computer InteractionTask (computing)user intent modelingRELEVANCE FEEDBACK020204 information systemsSEARCH0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingRelevance (information retrieval)Quality (business)Proactive searchmedia_common
researchProduct

Investigating Proactive Search Support in Conversations

2018

Conversations among people involve solving disputes, building common ground, and reinforce mutual beliefs and assumptions. Conversations often require external information that can support these human activities. In this paper, we study how a spoken conversation can be supported by a proactive search agent that listens to the conversation, detects entities mentioned in the conversation, and proactively retrieves and presents information related to the conversation. A total of 24 participants (12 pairs) were involved in informal conversations, using either the proactive search agent or a control condition that did not support conversational analysis or proactive information retrieval. Data c…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniStructure (mathematical logic)Settore INF/01 - InformaticaComputer sciencemedia_common.quotation_subject05 social sciencesControl (management)Common ground02 engineering and technology113 Computer and information sciencesvoice interfacesWorld Wide Web020204 information systems0202 electrical engineering electronic engineering information engineeringKey (cryptography)Natural (music)0501 psychology and cognitive sciencesConversationbackground speechspoken conversation supportproactive search050107 human factorsmedia_common
researchProduct

SearchBot: Supporting voice conversations with proactive search

2018

Searching during conversations and social interactions is becoming increasingly common. Although searching could be helpful for solving arguments, building common ground, and reinforcing mutual assumptions, it can also cause inter-actional problems. Proactive search approaches can enrich conversations with additional information without neglecting the shared and established social norms of being attentive to ongoing interaction. This demo showcases SearchBot, a tool that minimizes the issues associated with the practice of searching during conversations. It accomplishes this by tracking conversational background speech and then providing continuous recommendations of related documents and e…

ta113Computer science05 social sciencesCommon ground020207 software engineering02 engineering and technologyVoice user interfaceHuman–computer interaction0202 electrical engineering electronic engineering information engineering0501 psychology and cognitive sciencesProactive searchTracking (education)Background speechSpoken conversation support050107 human factorsVoice user interface
researchProduct