F
Fabio Crestani
Researcher at University of Lugano
Publications - 373
Citations - 7426
Fabio Crestani is an academic researcher from University of Lugano. The author has contributed to research in topics: Relevance (information retrieval) & Ranking (information retrieval). The author has an hindex of 40, co-authored 365 publications receiving 6237 citations. Previous affiliations of Fabio Crestani include University UCINF & University of Glasgow.
Papers
More filters
Journal ArticleDOI
Like It or Not: A Survey of Twitter Sentiment Analysis Methods
TL;DR: Fields related to sentiment analysis in Twitter including Twitter opinion retrieval, tracking sentiments over time, irony detection, emotion detection, and tweet sentiment quantification, tasks that have recently attracted increasing attention are discussed.
Journal ArticleDOI
“Is this document relevant?…probably”: a survey of probabilistic models in information retrieval
TL;DR: The basic concepts of probabilistic approaches to information retrieval are outlined and the principles and assumptions upon which the approaches are based are presented as mentioned in this paper, and various models proposed in the development of IR are described, classified, and compared using a common formalism.
Book ChapterDOI
A Test Collection for Research on Depression and Language Use
David E. Losada,Fabio Crestani +1 more
TL;DR: A novel early detection task is proposed and a novel effectiveness measure is defined to systematically compare early detection algorithms that takes into account both the accuracy of the decisions taken by the algorithm and the delay in detecting positive cases.
Proceedings ArticleDOI
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
TL;DR: This paper proposed a retrieval framework consisting of three components: question retrieval, question selection, and document retrieval, which takes into account the original query and previous question-answer interactions while selecting the next question.
Book ChapterDOI
eRISK 2017: CLEF Lab on Early Risk Prediction on the Internet: Experimental Foundations
TL;DR: This paper provides an overview of eRisk 2017, the main purpose of which was to explore issues of evaluation methodology, effectiveness metrics and other processes related to early risk detection.