Using technologies to support investigative interviewers in detecting deception
Lead Research Organisation:
University of Sussex
Department Name: Sch of Engineering and Informatics
Abstract
The project explores how investigative interviews (e.g., police, immigration, HMRC, benefits, etc.) can be facilitated by the provision of technological support. This support takes the form of a user interface that displays factoids relevant to the current stage of the interview, for example the name of a person the interviewee should know. These factoids are extracted from knowledge bases such as Wikipedia and also from the Web sites of relevant organisations. This Web Information Extraction is the key topic of this research. The challenge is to perform Named Entity Recognition and Co-reference Resolution on a whole Web site, taking into account the richer information present on the Web, such as formatting, position, titles and headings. These extracted entities for each Web page are then integrated to form an entity graph for the whole Web site that can be consumed by the user interface. A semi-supervised approach to training direct on HTML is proposed, guided by a lexicon extracted from Wikipedia.
Organisations
People |
ORCID iD |
| David Weir (Primary Supervisor) | |
| Colin Ashby (Student) |
Studentship Projects
| Project Reference | Relationship | Related To | Start | End | Student Name |
|---|---|---|---|---|---|
| EP/N509784/1 | 30/09/2016 | 29/09/2021 | |||
| 1955087 | Studentship | EP/N509784/1 | 01/03/2016 | 28/02/2021 | Colin Ashby |
| Description | This thesis presents the design, implementation and evaluation of an application designed to support interviewers in detecting deception. This application is evaluated in a job interviewing study using novice interviewers, which shows it to be a highly effective method of deception detection, correctly identifying 68.8% of deceivers overall, an increase of 107% and 97% over two baselines without application support, while also reducing false positives. |
| Exploitation Route | Deception detection researchers may be interested in our approach which enabled novice interviewers without specialised contextual knowledge to achieve a good deception detection result through the use of our supporting application Intek. |
| Sectors | Digital/Communication/Information Technologies (including Software) Financial Services and Management Consultancy Security and Diplomacy |
| Title | Deeper Web Entity Dataset |
| Description | A dataset based on DBpedia Org/Person tuples, that labels mentions of Persons from said Orgs website up to a depth of 3 pages. Various heuristic techniques are used to reduce false negatives. |
| Type Of Material | Database/Collection of data |
| Year Produced | 2019 |
| Provided To Others? | No |
| Impact | This dataset demonstrates the positive impact on F1 score, of the inclusion of HTML tag types, in real-world Named Entity Recognition. |
| Title | Web Entity Dataset |
| Description | A summarised collection of Web data that identifies Named Entities in the word/tag sequences. |
| Type Of Material | Database/Collection of data |
| Year Produced | 2018 |
| Provided To Others? | No |
| Impact | Enables the testing of the one of the main hypotheses of this research. |
| Title | Interview assistive user interface |
| Description | The system suggests deeper lines of questioning to an interviewer in real-time, based on initial snippets of information e.g. home address. |
| Type Of Technology | Webtool/Application |
| Year Produced | 2017 |
| Impact | It has played a part in driving the development of the associated theoretical work in Detecting Deception by my colleagues in Psychology. |
| Title | Webtool/Application - Interview assistive user interface v2 |
| Description | A significant update to the initial Interview Assistance app based on scenario-based interview transcripts, user input and expert input. Breadth and depth of Topics, as well as Topic accuracy have been improved. Speech interface has been rationalised. |
| Type Of Technology | Webtool/Application |
| Year Produced | 2020 |
| Impact | It will be used to design a trial to assess the effectiveness of interview assistance, especially with regard to lesser experiences interviewers. |
| Description | Sussex Impact Day 2018 |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Industry/Business |
| Results and Impact | Sussex Research Impact Day was an event featuring several speakers and presentations from University of Sussex to industry and academia with the aim of demonstrating the applications of our research. My input was a demonstration of the system I've been working on to various interested parties. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://www.sutori.com/story/sussex-impact-day-2018--DD34TpGt6ETTpQonTE9M1m4N |