API Modules

  • Text Summarization

  • Named Entity Recognition

  • Named Entity Salience

  • Keyphrase Extraction

Problem

You need to extract the most important information from a large amount of text.

Data sources: News articles.

Solution

Identify the relevant content and avoid information overload. Codeq's comprehensive offering of summarization and information technology allows you to encapsulate the important sentences of your texts, as well as to detect and disambiguate the most relevant Named Entities.

Our suite of NLP modules can be customized to your needs; we hand-tune the parameters of our solution until our API produces accurate and concise results.

Case Study

Next Level News is looking to add a new feature to their application that organizes news by subject, then displays relevant articles from a range of sources that cover the whole political spectrum.

As a key part of this feature, they want to display summaries of the news articles, giving their users a broad view of the information available.

Using our summarization tools, digestible, concise summaries become easily available.

Our named entity modules make it easy to link relevant entities to other subjects, giving Next Level News' users an easy way to stay engaged in the application.

“ White House chief of staff Mick Mulvaney and the president’s son-in-law and senior White House adviser Jared Kushner are trying to take the lead on the West Wing’s response to the impeachment inquiry, officials said. Mulvaney has led several meetings this week with White House officials on impeachment, which have included Kushner, a key conduit with the president’s re-election campaign. The Trump campaign has rolled out three impeachment-related ads in the last week, all echoing Trump’s language on corruption and accusing Democrats of leading a coup to remove him from office. ”

API Modules

  • Sentiment Classifier

  • Emotion Classifier

  • Sarcasm Classifier

  • Named Entity Recognition

Problem

You need to get an overall picture of the health of your brand, a quick snapshot you can use as a key performance indicator.

Data sources: Product reviews, email messages, business reviews, social media posts, news articles, blog posts, forums.

Solution

Extract rich insight into what users are expressing by identifying a wide range of language utterances.

Codeq’s API offers a granular approach to identify not only sentiment from texts, but also emotions, giving you a richer way to understand your users. Our sarcasm detection module works in combination with the sentiment and emotion detectors, something you won’t find anywhere else.

Case Study

Borneo is a large shopping site with an impressive number of reviews of many products.

Users have expressed dissatisfaction with the star rating system currently in place as it can be manipulated by companies who pay users to leave reviews.

Using the sentiment, emotion, and sarcasm classifiers, Borneo can create a rating system with more meaningful scores that measure things like enjoyment, satisfaction, and value.

Links to other product pages can be created easily using our named entity module.

“ My friend had the original SoundLink and it was phenomenal. So I thought I would have to get one. However, this new speaker sounds very bad! ”

“ The Nintendo Switch is a great console. My issue is that games are ridiculously expensive. So many are over priced. Also, the monthly subscription only gives you access to old fashion 80s games. ”

API Modules

  • Sentiment Classifier

  • Emotion Classifier

  • Sarcasm Classifier

  • Speech Act Classifier

Problem

You have large amounts of data taken from different customer communication channels and need to prioritize which pieces of feedback need your attention.

Data sources: Email messages, call center transcripts, chat transcripts, other customer communication channels.

Solution

Analyze your communication channels and spot messages with negative sentiments or emotions, so you can act and respond faster.

Give your users more attention when required.

Case Study

Patterson Holdings, an investment company, is receiving an overwhelming number of incoming messages from customers.

To deal with this influx, they want to build an internal tool that helps them determine which emails require an immediate response and to whom they should be routed.

Using the sentiment, emotion, and sarcasm classifier results, emails from distressed users can be routed to the appropriate specialists.

“ I'm writing because I'm worried about my retirement plan. I'm about to retire in a year but this nasty market crash has slashed my life investments in half. This is a disaster! What do you suggest I should do now? I really need your advice because I'm starting to panic. Please let me know as soon as possible. ”

API Modules

  • Speech Act Classifier

  • Task Extraction

Problem

You have large amounts of data taken from business communications and need to identify those requesting tasks or expressing commitments.

Data sources: Email messages, chat transcripts.

Solution

Analyze your unstructured content and extract important tasks and commitments.

Tasks are presented in a rich format that simplifies integration within your applications, including a concise representation of priority patterns and suggestions of possible actions to take to complete the tasks.

Case Study

Your Pal Friday, a service that offers remote executive assistance, is looking to add more functionality to the internal portion of their platform.

Using the task extractor, sentences that request scheduling can be funneled into a calendar application to automatically create meetings.

Sentences that request a phone call can be extracted and used to populate a VOIP application.

Sentences that express a need for electronic deliverables like reports can be used to jump start an email.

“ I have an urgent meeting this morning with the risk mitigations guys. Could you please send me the report you showed me yesterday about our emerging markets positions as soon as possible? Also, could you please tell Katie to come by my office this afternoon? I'd like to get her take on how next year's estimates are looking right now. By the way and before I forget, I promise I'll let you know about the birthday party this weekend asap. ”

API Modules

  • Abuse Classifier

Problem

You have a large amount of user-generated content that needs to be reviewed for abusive and harmful language.

Data sources: Posts on forums, social media, messages sent between users

Solution

Identify abusive and harmful content automatically using Codeq’s abuse classifier as part of your community management solution, saving you time and resources and preventing malicious users from discouraging, harassing, and insulting other community members.

Case Study

Focus on Facts is a web content publisher who has created a political fact checking website. Users have recently been given the ability to comment on posts, but the controversial nature of some of the content has attracted a group of people who are attacking other users using racist or hate speech remarks, as well as other spouting other types of abuse.

Some legitimate participants in the conversations of the comments section are now complaining about the site allowing this type of behavior, while other users have outright stopped participating and abandoned the community. Since this started happening the website has experienced a steady drop in traffic.

Using Codeq’s abuse classifier, insults, hate speech, racist or threat comments are automatically spotted.

The amount of time needed to moderate the comments section and identify toxic behaviour can be drastically reduced.

“What you just said is utterly retarded. Illegals just take good American jobs and are mostly criminals and rapists. Do not come to the US illegally or we'll have to teach you a lesson. Go back to your shitty country, Mexican! ”

“Oi freak why don't you shut up! You're just another sand nigger trying to destroy America. Take you BLM bullshit and shove it up your nasty ass. Go fuck yourself, mudslime! ”