Search

The eighth edition of the Italian Conference on Computational Linguistics (CLiC-it 2021) was held at Università degli Studi di Milano-Bicocca from 26th to 28th January 2022. After the edition of 2020, which was held in fully virtual mode due to the health emergency related to Covid-19, CLiC-it 2021 represented the first moment for the Italian research community of Computational Linguistics to meet in person after more than one year of full/partial lockdown.

This dataset contains relations extracted from the Italian Wikipedia by the WikiOIE framework. WikiOIE is based on UDPipe and the Universal Dependencies project for text processing. It easily allows customizing the information extraction (IE) approach to automatically extract triples (subject, predicate, object). This dataset contains relations extracted by a supervised approach based on self-training. The extraction process is provided in JSON format. Version 2 of the dataset was extracted using an improved version of the learning algorithm. The files of version 2 are identified by the suffix "_reg" in the file name. More information and the Java code are available here: https://github.com/pippokill/WikiOIE Self-training approach: Lucia Siciliani, Pierluigi Cassotti, Pierpaolo Basile, Marco de Gemmis, Pasquale Lops, and Giovanni Semeraro2021. Extracting Relations from Italian Wikipedia using Self-Training. In Proceedings of the Eighth Italian Conference on Computational Linguistics (CLiC-it2021). CEUR-WS. WikiOIE framework: Pierluigi Cassotti, Lucia Siciliani, Pierpaolo Basile, Marco de Gemmis, and Pasquale Lops. 2021. Extracting relations from Italian Wikipedia using unsupervised information extraction. In Proceedings of the 11th Italian Information Retrieval Workshop 2021 (IIR 2021). CEUR-WS.

On behalf of the Program Committee, a very warm welcome to the Seventh Italian Conference on Computational Linguistics (CLiC-it 2020). This edition of the conference is held in Bologna and organised by the University of Bologna. The CLiC-it conference series is an initiative of the Italian Association for Computational Linguistics (AILC) which, after six years of activity, has clearly established itself as the premier national forum for research and development in the fields of Computational Linguistics and Natural Language Processing, where leading researchers and practitioners from academia and industry meet to share their research results, experiences, and challenges.

In face-to-face interactions, advice acceptance depends on how it is presented, as well as a number of social factors. For example, some persons are inclined to accept advice from an expert if they possess little domain knowledge. In contrast, if such advice is unsolicited, persons might only accept advice from a trusted source, such as a family member. Whether these mechanisms also play a role in the recommender context is unknown, even though advice solicitation may be particularly important in domains where a recommender user seeks behavioral change (e.g. energy conservation, healthy eating). This study examines the role of advice solicitation (i.e. whether one asks for advice or simply receives it) and advice source (i.e. either explained in social terms or not) in our 'Saving Aid' energy recommender system. Through a web-based user study with 252 participants, we find that allowing users to solicit advice themselves increases their perceived level of trust with our energy recommender system, compared to users that are presented unsolicited advice. In turn, we find that trust positively affects user satisfaction levels, as well as the number of chosen energy-saving measures. We discuss how system designers should consider how advice is presented and in which context.

Music is often both personally and affectively meaningful to human listeners. However, little work has been done to create music recommender systems that take this into account. In this demo proposal, we present Spotivibes: a first prototype for a new color-based tagging and music recommender system. This innovative tagging system is designed to take the users' personal experience of music into account and allows them to tag their favorite songs in a non-intrusive way, which can be generalized to their entire library. The goal of Spotivibes is twofold: to help users better tag their playlists to get better playlists and to provide research data on implicit grouping mechanisms in personal music collections. The system was tested with a user study on 34 Spotify users.

Diversity-based recommender systems aim to select a wide rangeof relevant content for users, but diversity needs for users withdifferent personalities are rarely studied. Similarly, research onpersonality-based recommender systems has primarily focused onthe ‘cold-start problem’; few previous works have investigated howpersonality influences users’ diversity needs. This paper combinesthese two branches of research together: re-ranking for diversifica-tion, and improving accuracy using personality traits. Anchoredin the music domain, we investigate how personality informationcan be used to adjust the diversity degrees for people with differentpersonalities. We proposed a personality-based diversification algo-rithm to help enhance the diversity adjusting strategy according topeople’s personality information in music recommendations. Ouroffline and online evaluation results demonstrate that our proposedmethod is an effective solution to generate personalized recommen-dation lists that not only have relatively higher diversity as well asaccuracy, but which also lead to increased user satisfaction.

EVALITA is the evaluation campaign of Natural Language Processing and Speech Tools for the Italian language: since 2007 shared tasks have been proposed covering the analysis of both written and spoken language with the aim of enhancing the development and dissemination of resources and technologies for Italian. EVALITA is an initiative of the Italian Association for Computational Linguistics (AILC, http://www.ai-lc.it/) and it is supported by the NLP Special Interest Group of the Italian Association for Artificial Intelligence (AI*IA, http://www.aixia.it/) and by the Italian Association of Speech Science (AISV, http://www.aisv.it/). In this volume, we collect the reports of the tasks’ organisers and of the participants to all of the EVALITA 2016’s tasks, which are the following: ArtiPhone - Articulatory Phone Recognition; FactA - Event Factuality Annotation; NEEL-IT - Named Entity rEcognition and Linking in Italian Tweets; PoSTWITA - POS tagging for Italian Social Media Texts; QA4FAQ - Question Answering for Frequently Asked Questions; SENTIPOLC - SENTIment POLarity Classification. Notice that the volume does not include reports related to the IBM Watson Services Challenge organised by IBM Italy, but information can be found at http://www.evalita.it/2016/tasks/ibm-challenge. Before the task and participant reports, we also include an overview to the campaign that describes the tasks in more detail, provides figures on the participants, and, especially, highlights the innovations introduced at this year’s edition. An additional report presents a reflection on the outcome of two questionnaires filled by past participants and organisers of EVALITA, and of the panel “Raising Interest and Collecting Suggestions on the EVALITA Evaluation Campaign” held at CLIC-it 2015.

This article reports on the CBRecSys 2016 workshop, the third edition of the workshop on New Trends in Content-based Recommender Systems, co-located with RecSys 2016 in Boston, MA. Content-based recommendation has been applied successfully in many different domains, but it has not seen the same level of attention as collaborative filtering techniques have. Nevertheless, there are many recommendation domains and applications where content and metadata play a key role, either in addition to or instead of ratings and implicit usage data. The CBRecSys workshop series provides a dedicated venue for work dedicated to all aspects of content-based recommender systems.

User authentication and feedback gathering are crucial aspects for recommender systems. The most common implementations, a username / password login and star rating systems, require user interaction and a cognitive effort from the user. As a result, users opt to save their password in the interface and optional feedback with a star rating system is often skipped, especially for applica- tions such as video watching in a home environment. In this article, we propose an alternative method for user authentication based on facial recognition and an automatic feedback gathering method by detecting various face characteristics. Using facial recognition with a camera in a tablet, smartphone, or smart TV, the persons in front of the screen can be identified in order to link video watch- ing sessions to their user profile. During video watching, implicit feedback is automatically gathered through emotion recognition, attention measurements, and behavior analysis. An emotion finger- print, which is defined as a unique spectrum of expected emotions for a video scene, is compared to the recognized emotions in order to estimate the experience of a user while watching. An evaluation with a test panel showed that happiness can be most accurately detected and the recognized emotions are correlated with the user’s star rating.

Recommender systems are currently an ubiquitous presence on the web, helping us find relevant items in the ever-growing plethora of information available. However, there is not a one-size fits-all for recommender systems, and flexibility and control are crucial for enabling the possibility of adapting the recommender system to different user preferences. In this paper, we present the results of a study designed to assess user interaction with IntersectionExplorer (IEx), a multi-perspective tool for exploring conference paper recommendations. The study was conducted at the Digital Humanities 2016 Conference, an event with a rather large, heterogeneous, and not technology-oriented audience. The results obtained indicate that the IEx multi-perspective approach lends enough flexibility to accommodate different user preferences. When contrasting these results with a previous study conducted at a conference with a highly technological audience, it becomes apparent that the flexibility of IEx is key to empower users with different profiles to customize their approach to finding relevant recommendations. ispartof: pages:16-19 ispartof: Proceedings of the 4th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems co-located with ACM Conference on Recommender Systems (RecSys 2017) vol:1884 pages:16-19 ispartof: IntRS workshop @ RecSys 2017 location:Como, Italy status: published

While content-based recommendation has been applied successfully in many different domains, it has not seen the same level of attention as collaborative filtering techniques have. However, there are many recommendation domains and applications where content and metadata play a key role, either in addition to or instead of ratings and implicit usage data. For some domains, such as movies, the relationship between content and usage data has seen thorough investigation already, but for many other domains, such as books, news, scientific articles, and Web pages we still do not know if and how these data sources should be combined to provided the best recommendation performance. The CBRecSys 2016 workshop provides a dedicated venue for papers dedicated to all aspects of content-based recommendation.

Recent efforts in recommender systems research focus increasingly on human factors that affect acceptance of recommendations, such as user satisfaction, trust, transparency, and user control. In this paper, we present a scalable visualisation to interleave the output of several recommender engines with human-generated data, such as user bookmarks and tags. Such a visualisation enables users to explore which recommendations have been bookmarked by like-minded members of the community or marked with a specific relevant tag. Results of a preliminary user study (N=20) indicate that effectiveness and probability of item selection increase when users can explore relations between multiple recommendations and human feedback. In addition, perceived effectiveness and actual effectiveness of the recommendations as well as user trust into the recommendations are higher than a traditional list representation of recommendations. ispartof: pages:28-35 ispartof: Proceedings of the Joint Workshop on Interfaces and Human Decision Making for Recommender Systems co-located with ACM Conference on Recommender Systems (RecSys 2016) vol:1679 pages:28-35 ispartof: IntRS@RecSys location:Boston, USA date:16 Sep - 16 Sep 2016 status: published

User control has been recognised as an important feature in recommender system, as it allows users to steer the recommendation process. Most typical user controls relate to providing ratings, editing user data, and adjusting weights of the algorithm. The cognitive load of the user may increase when using more advanced user controls. We divided common user controls into three levels (high, middle, and low) and conducted a study (N=90) to investigate how different levels of user control affect cognitive load and quality of recommendations. We designed a visualisation on top of a music recommender system that incorporates three levels of control. The study results show that high level control tends to produce the best recommendations, while requiring the highest cognitive load. However, only participants with rich experience in recommender systems are more likely to tweak such high level control, while the majority of participants still prefers low and middle level control. We validated the robustness of our findings with three different algorithms. ispartof: pages:35-42 ispartof: Jin, Y., Cardoso, B. and Verbert, K., 2017, August. How do different levels of user control affect cognitive load and acceptance of recommendations?. In Proceedings of the 4th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems co-located with ACM Conference on Recommender Systems (RecSys 2017) vol:1884 pages:35-42 ispartof: IntRS workshop @ RecSys location:Como, Italy date:27 Aug - 27 Aug 2017 status: published