Projekt

Zurück zur Übersicht

Tracking Opinion Change Over Time (OpiTrack)

Gesuchsteller/in Crestani Fabio
Nummer 149809
Förderungsinstrument Projektförderung (Abt. I-III)
Forschungseinrichtung Facoltà di scienze informatiche Università della Svizzera italiana
Hochschule Università della Svizzera italiana - USI
Hauptdisziplin Informatik
Beginn/Ende 01.06.2014 - 31.05.2018
Bewilligter Betrag 247'334.00
Alle Daten anzeigen

Keywords (5)

temporal topic modelling; information retrieval; language modelling; santiment dynamics; opinion retrieval and mining

Lay Summary (Italienisch)

Lead
Negli ultimi anni il web ha visto una crescita esponenziale del cosiddetto “user-generated content”, ovvero di contenuto generato dagli utenti stessi, invece che da società' specializzate. Questo contenuto, presente in una moltitudine di piattaforme come Facebook, Twitter, YouTube, Goggle+, etc, rappresenta l’espressione delle opinioni personali degli utenti su prodotti, films, persone, ed altro.
Lay summary
L’obbiettivo principale del progetto e' di individuare user-generated content che esprime l’opinione di un utente su un certo topic predefinito. Nel corso del progetto svilupperemo modelli che individuano non solo se un documento esprime un’opinione, ma anche la polarità di questa opinione (ovvero se e’ positiva o negativa) in relazione al soggetto e a particolari caratteristiche del soggetto stesso. In aggiunta svilupperanno modelli in grado di tracciare temporalmente l’evoluzione dell’opinione e di collegarla ad eventi esterni che possono averla influenzata. L’obbiettivo finale e’ quello di sviluppare dei modelli in grado di prevedere l’evolversi delle opinioni degli utenti su certi argomenti di discussione, collegandole a possibili eventi esterni che possono influenzarle. I modelli verranno valutati con dati reali. 
Direktlink auf Lay Summary Letzte Aktualisierung: 29.04.2014

Verantw. Gesuchsteller/in und weitere Gesuchstellende

Mitarbeitende

Publikationen

Publikation
Emotional Reactions Prediction of News Posts
Giachanou Anastasia, Rosso Paolo, Mele Ida, Crestani Fabio (2018), Emotional Reactions Prediction of News Posts, in Proceedings of the 9th Italian Information Retrieval Workshop, Rome, ItalyEWIC, London, UK.
A Collection for Detecting Triggers of Sentiment Spikes
Giachanou Anastasia, Mele Ida, Crestani Fabio (2017), A Collection for Detecting Triggers of Sentiment Spikes, in Proceedings of the 40th International Conference on Research and Development in Information Retrieva, 1249-1252, ACM, New York1249-1252.
Comparative opinion mining: a review
Varathan Kasturi Dewi, Giachanou Anastasia, Crestani Fabio (2017), Comparative opinion mining: a review, in Journal of the Association for Information Science and Technology, 68(4), 811-829.
Emerging Sentiment Language Model for Emotion Detection
Giachanou Anastasia, Rangel Francisco, Crestani Fabio, Rosso Paolo (2017), Emerging Sentiment Language Model for Emotion Detection, in Proceedings of the 4th Italian Conference on Computational Linguistics, 1-6, CEUR-WS, London, UK1-6.
USI Participation at SMERP 2017 Text Retrieval Task
Giachanou Anastasia, Mele Ida, Crestani Fabio (2017), USI Participation at SMERP 2017 Text Retrieval Task, in Proceedings of the 1st Exploitation of Social Media for Emergency Relief and Preparedness (SMERP) Wo, 52-60, ACM, New York52-60.
USI Participation at SMERP 2017 Text Summarization Task
Giachanou Anastasia, Mele Ida, Crestani Fabio (2017), USI Participation at SMERP 2017 Text Summarization Task, in Proceedings of the 1st Exploitation of Social Media for Emergency Relief and Preparedness Workshop (, 99-103, ACM, New York99-103.
Explaining Sentiment Spikes in Twitter
Giachanou Anastasia, Crestani Fabio (2016), Explaining Sentiment Spikes in Twitter, in Proceedings of the 25th International Conference on Information and Knowledge Management, 2263-2268, ACM, New York2263-2268.
Like It or Not: A Survey of Twitter Sentiment Analysis Methods
Giachanou Anastasia, Crestani Fabio (2016), Like It or Not: A Survey of Twitter Sentiment Analysis Methods, in ACM Computing Surveys, 49(2), 28-28.
Opinion retrieval in Twitter using stylistic variations
Giachanou Anastasia, Crestani Fabio (2016), Opinion retrieval in Twitter using stylistic variations, in Proceedings of the 31st Annual Symposium on Applied Computing, 1077-1079, ACM, New York1077-1079.
Opinion Retrieval in Twitter: Is Proximity Effective?
Giachanou Anastasia, Crestani Fabio (2016), Opinion Retrieval in Twitter: Is Proximity Effective?, in Proceedings of the 31st Annual Symposium on Applied Computing, 1146-1151, ACM, New York1146-1151.
Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter
Giachanou Anastasia, Harvey Morgan, Crestani Fabio (2016), Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter, in Proceedings of the 38th European Conference on Advances in Information Retrieval, 466-478, Springer, Berlin466-478.
University of Lugano at TREC 2015: Contextual Suggestion and Temporal Summarization Tracks
Aliannejadi Mohammad, Bahrainian Seyed Ali, Giachanou Anastasia, Crestani Fabio (2015), University of Lugano at TREC 2015: Contextual Suggestion and Temporal Summarization Tracks, 1-6, ACM, New York1-6.
Opinions in federated search: University of lugano at TREC 2014 federated web search track
Giachanou Anastasia, Markov Ilya, Crestani Fabio (2014), Opinions in federated search: University of lugano at TREC 2014 federated web search track, 1-8, ACM, New York1-8.

Zusammenarbeit

Gruppe / Person Land
Formen der Zusammenarbeit
Monash University Australien (Ozeanien)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
- Publikation

Wissenschaftliche Veranstaltungen

Aktiver Beitrag

Titel Art des Beitrags Titel des Artikels oder Beitrages Datum Ort Beteiligte Personen
31st Annual Symposium on Applied Computing Vortrag im Rahmen einer Tagung Opinion retrieval in Twitter using stylistic variations 01.10.2017 Pisa, Italien Crestani Fabio; Giachanou Anastasia;
40th International Conference on Research and Development in Information Retrieval Poster A Collection for Detecting Triggers of Sentiment Spikes 01.08.2017 Tokyo, Japan Crestani Fabio; Giachanou Anastasia;
4th Italian Conference on Computational Linguistics Vortrag im Rahmen einer Tagung Emerging Sentiment Language Model for Emotion Detection 01.05.2017 Rome, Italien Giachanou Anastasia;
39th European Conference on Advances in Information Retrieval Poster Sentiment Propagation for Predicting Reputation Polarity 01.04.2017 Aberdeen, Grossbritannien und Nordirland Crestani Fabio; Giachanou Anastasia;
31st Annual Symposium on Applied Computing Poster Opinion Retrieval in Twitter: Is Proximity Effective? 01.10.2016 Pisa, Italien Giachanou Anastasia;
25th International Conference on Information and Knowledge Management Vortrag im Rahmen einer Tagung Explaining Sentiment Spikes in Twitter 01.10.2016 Indianapolis, Vereinigte Staaten von Amerika Giachanou Anastasia; Crestani Fabio;
39th International Conference on Research and Development in Information Retrieval Vortrag im Rahmen einer Tagung Tracking Sentiment by Time Series Analysis 01.07.2016 Pisa, Italien Giachanou Anastasia; Crestani Fabio;
38th European Conference on Advances in Information Retrieval Vortrag im Rahmen einer Tagung Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter 01.03.2016 Padua, Italien Giachanou Anastasia;


Abstract

Recent years have seen the rapid growth of social media platforms that enable people to express their thoughts and opinions on the web and share them with other users. Many people write their opinion about products, movies, people or events on blogs, forums or review sites. In this project we will extend the latest models of opinion retrieval and sentiment analysis by incorporating time in the opinion analysis. We will develop models that track sentiment over time also covering different aspects of a topic. We will also develop models that will attempt to predict the sentiment change toward a topic at a certain time in future. The models developed will be evaluated with real data.
-