Entity Retrieval and Text Mining for Online Reputation Monitoring

TL;DR

This paper introduces new methods for entity retrieval and text mining to enhance online reputation monitoring by enabling flexible, entity-centric searches and relationship analysis, addressing limitations of current aggregate-based approaches.

Contribution

It proposes the integration of entity-relationship retrieval and text-based prediction capabilities into ORM, along with tailored disambiguation and sentiment analysis methods.

Findings

Developed methods for extracting and retrieving entity-centric information.

Enhanced ORM with entity-relationship search capabilities.

Improved prediction of entity popularity based on news and social media.

Abstract

Online Reputation Monitoring (ORM) is concerned with the use of computational tools to measure the reputation of entities online, such as politicians or companies. In practice, current ORM methods are constrained to the generation of data analytics reports, which aggregate statistics of popularity and sentiment on social media. We argue that this format is too restrictive as end users often like to have the flexibility to search for entity-centric information that is not available in predefined charts. As such, we propose the inclusion of entity retrieval capabilities as a first step towards the extension of current ORM capabilities. However, an entity's reputation is also influenced by the entity's relationships with other entities. Therefore, we address the problem of Entity-Relationship (E-R) retrieval in which the goal is to search for multiple connected entities. This is a challenging problem which traditional entity search systems cannot cope with. Besides E-R retrieval we also believe ORM would benefit of text-based entity-centric prediction capabilities, such as predicting entity popularity on social media based on news events or the outcome of political surveys. However, none of these tasks can provide useful results if there is no effective entity disambiguation and sentiment analysis tailored to the context of ORM. Consequently, this thesis address two computational problems in Online Reputation Monitoring: Entity Retrieval and Text Mining. We researched and developed methods to extract, retrieve and predict entity-centric information spread across the Web.