is an assistant professor at the ICT Departmental Unit of the Polytechnic Institute of Tomar (IPT) and member of LIAAD-INESC TEC, the Artificial Intelligence and Decision Support Lab of U. Porto.
He is PhD in Computer Science by the University of Porto (U. Porto). His work on temporal information retrieval led him to win the Fraunhofer Portugal Challenge 2013 and to be distinguished as an “outstanding” researcher by the INESC TEC research lab.
He has over 10 years of research experience in Information Retrieval and Text Mining.
In 2018, he has been awarded the best short paper award at ECIR'18 (40th International Conference on Information Retrieval) for the paper entitled "A Text Feature Based Automatic Keyword Extraction Method for Single Documents" and the 1st prize of the Arquivo.pt Award for his project Tell Me Stories [http://tellmestories.pt].
He is an editorial board member of the Information Processing & Management Journal (Elsevier), co-chaired international conferences and workshops, being also a program committee member of several international conferences.
Contact him at email@example.com
Automatic Generation of Timeline Summaries
During the last decade, we have been witnessing an exponential growth of the volume of data posing new challenges for those who aim to understand a given event in a timely manner.
For instance, following the media coverage of long-lasting events like political or economic crises, natural disasters or climate changes can be oftentimes confusing and demanding.
One possible solution is to frame these stories into appropriate timelines. However, manually building these timelines may be time-consuming for any human interested in having access to a quick glimpse on a given topic.
One possible solution to overcome this problem is to automatically summarize large amount of texts into consistent narratives, an active topic of research in academia.
In this talk, we begin by reviewing the state-of-the-art in event summarization to get an overview of the field. We will then present our work on automatically generating timeline summaries.
Through different use cases, we will highlight the importance of extracting relevant keywords from texts in various domains as a means to automatically generate summaries.
We will conclude this talk by discussing future challenges related to the creation of personal stories.
09.00 - 10:30 - Session 1:
09.00 - 09.20 - Welcome Message - Opening remarks;
- 09.20 - 09.40 - Enriching Product Catalogs with User Opinions;
- 09.40 - 10.10 - Beyond Accuracy in Link Prediction;
- 10.10 - 10.30 - AspeRa: Aspect-based Rating Prediction Model;
10.30 - 11:00 - Coffe break
11.00 - 12:30 - Session 2:
11.00 - 11.50 - Keynote talk: Automatic Generation of Timeline Summaries;
- 11.50 - 12.10 - Building User Profiles Based On Fuzzy Preferences Relations;
- 12.10 - 12.20 - Open Discussion;
- 12.20 - 12.30 - Closing remarks.
Call for Papers:
In order to improve the web experience of the users, classic personalization technologies (e.g., recommender systems) and search engines usually rely on static schemes. Indeed, users are allowed to express ratings in a fixed range of values for a given catalogue of products, or to express a query that usually returns the same set of webpages/products for all the users.
With the advent of social media, users have been allowed to create new content and to express opinions and preferences through likes and textual comments. Moreover, the social network itself can provide information on who influences whom. Being able to mine usage and collaboration patterns in social media and to analyze the content generated by the users opens new frontiers in the generation of personalization services and in the improvement of search engines. Moreover, recent technological advances, such as deep learning, are able to provide a context to the analyzed data. Even though social media platforms offer an abundance of data, recent regulations like the GDPR, limit the way in which personal data is collected, treated, and stored. Hence, users’ consent and privacy has become a prominent and timely issue.
Our workshop solicits contributions in all topics related to employing social media for personalization and search purposes, focused (but not limited) to the following list:
- Recommender systems;
- Search and tagging;
- Query expansion;
- User modeling and profiling;
- Advertising and ad targeting;
- Content classification, categorization, and clustering;
- Using social network features/community detection algorithms for personalization and search purposes;
- Privacy-aware algorithms.
Types of contribution:
We will consider three different submission types, all in the LNCS format: regular (14 pages), short (8 pages) and extended abstracts (4 pages).
Research and position papers (regular or short) should be clearly placed with respect to the state of the art and state the contribution of the proposal in the domain of application, even if presenting preliminary results. In particular, research papers should describe the methodology in detail, experiments should be repeatable, and a comparison with the existing approaches in the literature should be made where possible.
Position papers(short) should introduce novel point of views in the workshop topics or summarize the experience of a researcher or a group in the field.
Practice and experience reports (short) should present in detail the real-world scenarios in which social media is employed for personalization and search purposes.
Demo proposals (extended abstract) should present the details of a prototype or complete application that employs social media for personalization and search purposes. The systems will be demonstrated to the workshop attendees.
The reviewing process will be coordinated by the organizers. Each paper will receive three reviews: two externals to the organizing committee and one internal. The external reviewers will be contacted according to their expertise in the paper topic.
All submission must be written in English and follow the ECIR paper guidelines. All papers must be formatted according to the LNCS format style. Papers should be submitted in PDF format, electronically, using the EasyChair submission system, available at: SoMePeAS@EasyChair.
All accepted papers will be made available on the workshop website together with the material generated during the meeting. The SoMePeAS 2019 Workshop proceedings will also be available in a volume (whose details will be given soon), and indexed on DBLP and Scopus. Authors of selected papers will be invited to submit an extended version in a journal special issue.