Abstract
In a world increasingly present online, people are leaving a digital footprint, with valuable information scattered on the Web, in an unstructured manner, beholden to the websites that keep it. While there are potential harms in being able to access this information readily, such as enabling corporate surveillance, there are also significant benefits when used, for example, in journalism or investigations into Human Trafficking. This paper presents an approach for retrieving domain-specific information present on the Web using Social Media platforms as a gateway to other content existing on any website. It begins by identifying relevant profiles, then collecting links shared in posts to webpages related to them, and lastly, extracting and indexing the information gathered. The tool developed based on this approach was tested for a case study in the domain of Human Trafficking, more specifically in sexual exploitation, showing promising results and potential to be applied in a real-world scenario.

Abstract
In a world increasingly present online, people are leaving a digital footprint, with valuable information scattered on the Web, in an unstructured manner, beholden to the websites that keep it. While there are potential harms in being able to access this information readily, such as enabling corporate surveillance, there are also significant benefits when used, for example, in journalism or investigations into Human Trafficking. This paper presents an approach for retrieving domain-specific information present on the Web using Social Media platforms as a gateway to other content existing on any website. It begins by identifying relevant profiles, then collecting links shared in posts to webpages related to them, and lastly, extracting and indexing the information gathered. The tool developed based on this approach was tested for a case study in the domain of Human Trafficking, more specifically in sexual exploitation, showing promising results and potential to be applied in a real-world scenario.

Abstract

Abstract
A patient’s ability to recall and retrieve health information contributes to a better health management. HealthTalks was developed to address these issues by recording a summary of a medical appointment, uttered by the physician, and transcribing it. For each appointment, the user can also take free-text notes. Nowadays, search engines have become a ubiquitous part of everyone’s life and are expected on most applications. Here, we describe the development of a search engine for HealthTalks. The app’s characteristics demand a lightweight and offline engine, which requires a specific solution rather than an existing library or service. Our approach combines SQLite’s Full-Text Search 4 module, which includes n-gram indexing, with traditional information retrieval techniques to rank the documents. We created a test collection with summaries of clinical appointments (our documents), information needs, search queries, and relevance assessments for an initial search engine evaluation. Using this test collection, we assessed performance using NDCG@10, the first rank position of a totally relevant result, and query latency. Results are promising, with an average NDCG of 0.97. The median rank position of the first relevant result varies between 1.9 and 1.95, depending on the use of 4-gram character tokenization, an aspect that did not significantly affect the results. We expect this work to be useful for future developments of full-text search engines in mobile environments.

Abstract