2020
Autores
Lopes, CT; Ramos, E;
Publicação
CHIIR'20: PROCEEDINGS OF THE 2020 CONFERENCE ON HUMAN INFORMATION INTERACTION AND RETRIEVAL
Abstract
Health literacy affects how people understand health information and, therefore, should be considered by search engines in health searches. In this work, we analyze how the level of health literacy is related to the eye movements of users searching the web for health information. We performed a user study with 30 participants that were asked to search online in the context of three work task situations defined by the authors. Their eye interactions with the Search Results Page and the Result Pages were logged using an eye-tracker and later analyzed. When searching online for health information, people with adequate health literacy spend more time and have more fixations on Search Result Pages. In this type of page, they also pay more attention to the results' hyperlink and snippet and click in more results too. In Result Pages, adequate health literacy users spend more time analyzing textual content than people with lower health literacy. We found statistical differences in terms of clicks, fixations, and time spent that could be used as a starting point for further research. That we know of, this is the first work to use an eye-tracker to explore how users with different health literacy search online for health-related information. As traditional instruments are too intrusive to be used by search engines, an automatic prediction of health literacy would be very useful for this type of system.
2020
Autores
Santos, PM; Lopes, CT;
Publicação
Advances in Information Retrieval - 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14-17, 2020, Proceedings, Part II
Abstract
Medico-scientific concepts are not easily understood by laypeople that frequently use lay synonyms. For this reason, strategies that help users formulate health queries are essential. Health Suggestions is an existing extension for Google Chrome that provides suggestions in lay and medico-scientific terminologies, both in English and Portuguese. This work proposes, evaluates, and compares further strategies for generating suggestions based on the initial consumer query, using multi-concept recognition and the Unified Medical Language System (UMLS). The evaluation was done with an English and a Portuguese test collection, considering as baseline the suggestions initially provided by Health Suggestions. Given the importance of understandability, we used measures that combine relevance and understandability, namely, uRBP and uRBPgr. Our best method merges the Consumer Health Vocabulary (CHV)-preferred expression for each concept identified in the initial query for lay suggestions and the UMLS-preferred expressions for medico-scientific suggestions. Multi-concept recognition was critical for this improvement. © Springer Nature Switzerland AG 2020.
2020
Autores
Koch, I; Ribeiro, C; Lopes, CT;
Publicação
Digital Libraries for Open Knowledge - 24th International Conference on Theory and Practice of Digital Libraries, TPDL 2020, Lyon, France, August 25-27, 2020, Proceedings
Abstract
Archives are faced with great challenges due to the vast amounts of data they have to curate. New data models are required, and work is underway. The International Council on Archives is creating the RiC-CM (Records in Context), and there is a long line of work in museums with the CIDOC-CRM (CIDOC Conceptual Reference Model). Both models are based on ontologies to represent cultural heritage data and link them to other information. The Portuguese National Archives hold a collection with over 3.5 million metadata records, described with the ISAD(G) standard. The archives are designing a new linked data model and a technological platform with applications for archive contributors, archivists, and the public. The current work extends CIDOC-CRM into ArchOnto, an ontology-based model for archives. The model defines the relevant archival entities and properties and will be used to migrate existing records. ArchOnto accommodates the existing ISAD(G) information and takes into account its implementation with current technologies. The model is evaluated with records from representative fonds. After the test on these samples, the model is ready to be populated with the semi-automatic transformation of the ISAD records. The evaluation of the model and the population strategies will proceed with experiments involving professional and lay users. © 2020, Springer Nature Switzerland AG.
2020
Autores
Antunes, H; Lopes, CT;
Publicação
PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20)
Abstract
Looking for health information is one of the most popular activities online. However, the specificity of language on this domain is frequently an obstacle to comprehension, especially for the ones with lower levels of health literacy. For this reason, search engines should consider the readability of health content and, if possible, adapt it to the user behind the search. In this work, we explore methods to assess the readability of health content automatically. We propose features capable of measuring the specificity of a medical text and estimate the knowledge necessary to comprehend it. The features are based on information retrieval metrics and the log-likelihood of a text with lay and medico-scientific language models. To evaluate our methods, we built and used a dataset composed of health articles of Simple English Wikipedia and the respective documents in ordinary Wikipedia. We achieved a maximum accuracy of 88% in binary classifications (easy versus hard-to-read). We found out that the machine learning algorithm does not significantly interfere with performance. We also experimented and compared different features combinations. The features using the values of the log-likelihood of a text with lay and medico-scientific language models perform better than all the others.
2020
Autores
Fernandes, M; Rodrigues, J; Lopes, CT;
Publicação
Digital Libraries for Open Knowledge - 24th International Conference on Theory and Practice of Digital Libraries, TPDL 2020, Lyon, France, August 25-27, 2020, Proceedings
Abstract
Research data management is the basis for making data more Findable, Accessible, Interoperable and Reusable. In this context, little attention is given to research data in image format. This article presents the preliminary results of a study on the habits related to the management of images in research. We collected 107 answers from researchers using a questionnaire. These researchers were PhD students, fellows and university professors from Life and Health Sciences, Exact Sciences and Engineering, Natural and Environmental Sciences and Social Sciences and Humanities. This study shows that 83.2% of researcher use images as research data, however, its use is generally not accompanied by a guidance document such as a research data management plan. These results provide valuable insights into the processes and habits regarding the production and use of images in the research context. © 2020, Springer Nature Switzerland AG.
2021
Autores
Couto, L; Lopes, CT;
Publicação
WEB CONFERENCE 2021: COMPANION OF THE WORLD WIDE WEB CONFERENCE (WWW 2021)
Abstract
Wikipedia is an online, free, multi-language, and collaborative encyclopedia, currently one of the most significant information sources on the web. The open nature of Wikipedia contributions raises concerns about the quality of its information. Previous studies have addressed this issue using manual evaluations and proposing generic measures for quality assessment. In this work, we focus on the quality of health-related content. For this purpose, we use general and health-specific features from Wikipedia articles to propose health-specific metrics. We evaluate these metrics using a set of Wikipedia articles previously assessed by WikiProject Medicine. We conclude that it is possible to combine generic and specific metrics to determine health-related content's information quality. These metrics are computed automatically and can be used by curators to identify quality issues. Along with the explored features, these metrics can also be used in approaches that automatically classify the quality of Wikipedia health-related articles.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.