Areas in NLP
opinion analysis, text mining
Whether you are a CEO, member of a government or a personality, it is important to ensure your eReputation. With the development of social networks, we have access to a wealth of information on our eReputation, on what people think of us. But, in return, what we say and what we do spread in large-scale.
There are listening platforms identifying a list of articles talking about a brand, a business or a personality and offering opinion analysis tools. The problem with these solutions is that they apply a very wide crawl and can report data without much interest. The completeness of these platforms can be brought into question. Although the approach certainly is of interest in “quantifying” data, we cannot get something out of it in the “qualified” perspective. First, the result is often a hodgepodge of heterogeneous texts, often highly redundant, with little real opinions expressed (hence the category “neutral” as many opinions analysis systems put next to “positive” and “negative”) category has little value in most cases. Finally, eReputation platforms offering a function of “sentiment analysis” do this for the entire document, which quickly becomes unusable when several points of view are expressed in the same document.
Trooclick’s Opinion-Driven Search Engine uses natural language processing (NLP) technology to gather quotes from online sources of news and opinions – including content from publishers, blogs, and Twitter. After quotes are extracted, the speakers are categorized (categories include executives, analysts, politicians, journalists…).
The original business plan was to develop the first automated fact-checking app for financial news. « Fact checking is the task of assessing the truthfulness of claims made by public figures such as politicians, pundits, etc. It is commonly performed by journalists employed by news organisations in the process of news article creation. Fact-checking is a time-consuming process » (Vlachos & Riedel 2014)
But, the plug-in worked so well that it didn’t find any errors. The reason is that financial companies know their words are scrutinized by regulators and don’t dare to make misstatements. Influential speakers prefer to use omission rather than errors. The way you combat that problem is by presenting different points of view.
Trooclick’s Opinion-Driven Search Engine can be a solution for companies in social media or search giants such as LinkedIn or Yahoo. It can be also a solution for b-to-b-to-b approach in which a customer could use Trooclick’s technology to provide its own client companies with easily digestible media monitoring.
Trooclick currently has a team of 18 full-time people including 10 engineers and PhD.
1 PhD in Semantic Web
5 NLP engineers
Research and Development issues
Actually, R&D projects in the Artificial Intelligence field :
- automated quotes collection
- automated named entity recognition and classification in speaker categories (journalist, politician…)
- automated evaluation and scoring of quotes (variety of criteria including instances of anticipation, contrast, causality, etc.)
The Trooclick’s Opinion-Driven Search Engine is protected by an US patent obtained on March 2015.
In the long run, Trooclick will develop automatically generated viewpoint summaries. With a huge chunk of readers never making it past the headline, Trooclick sees it as important to quickly summarize the major viewpoints on an issue in the first couple lines of each entry.
In April 2013, Trooclick received financial support from the BPI (French public investment bank) and in June 2013 the French government granted it the Status of “Young Innovative Company” (JEI), recognizing its innovative nature.
Marketing and Sales Assistant
+33 (0)6 59 31 56 59