The power of sentiment analysis in Contact Centers  

In customer service, every interaction between the customer and the agent has the potential to build or deteriorate the company’s image. Data analysis can be a determining factor by examining these interactions on a large scale and providing insights on how to optimize these exchanges. In this article, we will address the significant role of data analysis, particularly in the context of Amazon Connect. We will explore how Amazon Connect harnesses the power of data analysis and sentiment analysis to understand customer behavior, enhance agent performance, and optimize contact center operations. 

Amazon connect Contact Lens:  

The “Contact Lens” AI in Amazon Connect enables sentiment analysis throughout conversations between the customer and the agent. This tool allows contact centers to gain in-depth insights into customer behavior. 

 Contact Lens provides: 

  • Transcription of calls between the agent and the customer 
  • Sentiment analysis 
  • Real-time and post-call conversation categorization. 

Read our article on sentiment analysis in Customer Relations.

Real-time sentiment analysis for agent performance monitoring:

Managers have the ability to analyze real-time interactions with customers to determine the emotional tone of conversations. Through the identification of sentiments such as frustration, satisfaction, or confusion, immediate responses and appropriate solutions can be provided, thus contributing to the improvement of the customer experience. For example, in case of frustration, a real-time alert can be sent to the manager, giving them the opportunity to listen to the conversation and intervene if necessary to assist the agent. By assessing customer sentiments during live interactions, supervisors can intervene as soon as emotions take a negative turn, ensuring a more positive customer experience. 

Tailoring training using sentiment information:

Amazon Connect offers tools that enable contact center managers to make decisions regarding training programs. Sentiment data collected by Amazon Connect provides valuable insights for agent training. For instance, by identifying recurring issues, frequent concerns, or negatively themed topics in customer interactions, contact centers can tailor their training programs. This ensures that agents are equipped to handle specific scenarios more effectively. Sentiment analysis also helps identify areas where agents consistently excel or face challenges. This information can be leveraged to customize training programs and enhance overall agent performance. 

Strategic decision-making using sentiment trends:

The data analysis tools of Amazon Connect enable strategic decision-making based on sentiment trends. For instance, identifying long-term trends of positive or negative sentiments related to specific issues or products can inform and guide decisions regarding product improvements, service adjustments, or marketing strategies, ensuring a more customer-centric approach. 


The integration of data analytics and sentiment analysis by Amazon Connect can reshape your customer service experience. By understanding customer behavior, improving agent performance, and optimizing overall operations, businesses using Amazon Connect can deliver more personalized and efficient services. 

This article is published by  

Rita Ammanouil,

Solution Architect - Activeo

These articles might interest you

Sentiment analysis: a new trend in the service of the customer experience

Customers are the greatest source of learning for a business. If a customer is unhappy or happy, there’s something about the company, product, or customer service experience that made them that way. With millions of calls recorded, contact centers contain valuable information about a company’s customers. Unlike manual investigation, Sentiment Analysis tools can extract this information from recordings of customer conversations in an efficient and fast way. In this article, we discuss sentiment analysis in a contact center and answer several important questions about this topic, starting with what is sentiment analysis, how does it work and how to take advantage of it?

What is sentiment analysis in a contact center?

Contact centers are increasingly offering native sentiment analysis tools that analyze conversations (voice and chat) between customers and agents. Among these contact centers, we cite AWS Connect and Genesys Cloud which offer this functionality. Most importantly, this feature can be activated in a few clicks, configured quickly, and requires no prior knowledge of coding, machine learning, or underlying algorithms. Subsequently, all conversations are analyzed in order to deduce the feelings of the interlocutors, which are the agent and the customer in a contact center.

By definition, sentiment analysis is an automatic text classification tool to infer, as the name suggests, sentiment. Basically, the inferred sentiment can be classified into three categories: positive, negative, or neutral sentiment. In this case, it is the dominant feeling or the polarity of the text. Sentiment analysis can also go beyond polarity and detect more precise feelings such as anger, disgust, fear, surprise… Figures 1 and 2 show the sentiment analysis interface of AWS Connect and Genesys Cloud respectively. AWS Connect points the sentiment score via either a smiley, neutral, or sad face for each reply in the conversation between the customer and the agent, while Genesys cloud uses the thumbs up or thumbs down emoticon placed on the record.

Figure 1: Ex. sentiment analysis from AWS Connect
Sentiment analysis

Figure 2: Ex. Genesys Cloud Sentiment Analysis

How does it work?

Any sentiment analysis tool is based on two main pillars: natural language processing algorithms and machine learning algorithms. Sentiment analysis systems are mainly based on the analysis of textual content. As a first step, call recordings must be converted into text and more precisely into conversation between interlocutors. This step is also known as the transcription step. Keywords and key phrases are then extracted from the text for each replica. Via “machine learning”, an individual score is assigned to each replica. Finally, a general score is attributed to the conversation which is in general the average of the individual scores. To summarize, the steps are as follows:

  • Transcribe voice recording to agent and customer chat text
  • Extract phrases and keywords
  • Assign a sentiment score for each line
  • Combine the individual scores to get a conversation score

To be able to assign a sentiment score in the third step, the sentiment analysis system uses a “sentiment dictionary”. This is a very large collection of adjectives (ex: good, bad, wonderful, awful, happy, sad) and phrases (ex: I like, I don’t like, it’s great, it doesn’t suit me, it’s wonderful, it’s awful) that have been assigned a score by hand. So, for example, phrases that contain or sound like “Like” will be classified as “positive” while phrases containing “I don’t like” will be classified as “negative.”

Contrary to what some might think, sentiment analysis is not based on pitch or loudness. However, we can measure the loudness of the speech of the customer and the agent and use this information to complete the sentiment analysis. For example, a high sound intensity accompanied by a negative feeling can be a strong indicator of dissatisfaction. However, you will have to read or hear this part of the conversation to try to understand and solve the problem.

How to benefit from sentiment analysis in a Contact Center?

There are certainly several advantages to using sentiment analysis tools in a contact center. For starters, managers gain in efficiency and a huge amount of time because they no longer need to manually analyze sentiment and listen in on every conversation.

As Bill Gates said, “Your most unhappy customers are your greatest source of learning”. So, a first course of action is to spot conversations with a high level of negative feelings. Then, we can use these conversations to better coach agents and provide new guidelines in favor of the customer. We can also use these conversations to offer personalized service to the customer and better meet their needs. In addition to this, we can identify the agents with the highest levels of positive emotions and positive conversations to reward them, encourage them and make them ambassadors. Finally, it can be interesting to visualize sentiment trends and correlations such as:

  • Sentiment trends for an agent, for a team, for a client
  • Trends in sentiment based on a product, service, or marketing campaign
  • The correlation between the customer’s feeling and the duration of the call, the duration of silence (non-talk time).

Based on this information, we are able to make relevant decisions to improve the feeling of both the customer and the agent.


In conclusion, sentiment analysis in a contact center brings unprecedented added value to the brand, helping it to obtain important information on what makes the customer happy or unhappy. This functionality, which was then expensive, complex and difficult to implement a few years ago, is now available, affordable, and simple to implement. To take advantage of it and to find out more, contact us to discuss these subjects for which Activeo has in-depth expertise, and we will present you with use cases and feedback.

Conversational agents: Why such a craze?

Whether you are in Customer Relations, Marketing, Digital, IT or Communication, you have not been able to escape either the sudden and generalized rush of these applications or the abundance of actors and initiatives in this field.
To go beyond the buzz, we propose to understand this manifestation of digital disruption from all angles….

Like many people, to varying degrees, you may be wondering about the scope, relevance and conditions for implementing a conversational agent (also called a bot) within your organization:

What are the contributions and promises, the deadlines to be expected, who are the publishers, for which uses, the good practices,…
It is also possible that among the wealth of information at your disposal, you do not necessarily know where or how to start!

We tell you (almost) everything, it’s here!

From science fiction to reality


Who would have believed 10 or 20 years ago that such a technological revolution was possible?
While Artificial Intelligence is more than half a century old, its applications related to optimization and automation in customer relations are still more recent.

Studies speak for themselves: 85% of Customer-Brand interactions will involve the use of Chatbot in 2022*.

It is true that conversational robots have been on the rise for several years now. Time optimization, service improvement and brand image enhancement are the main added values of innovation in the interaction between the customer, the user and the brand.

But how to explain such a craze?

  • First of all, the rise of AI allowing a much better personalization of exchanges (natural/human language understanding, contextualization, machine learning…)
  • Also the modification of customer uses and behaviors (digitalization, social networks & instant messaging, …)
    Examples: Search for your train schedule, track your package, check the latest health instructions, etc., now possible at any time, 24 hours a day, 7 days a week.
  • Benefits appreciated by brands (automation of responses to the most recurrent and/or non-value-added requests, cost reduction, unclogging of pending contacts, etc.)
  • And finally, the grail, increasing customer satisfaction by responding to the need for immediacy and autonomy.

Conversational robots arrive to reinforce human interaction

Or how the bots responded during this health crisis Covid-19


When the first national containment came into effect on March 17, many of us were wondering about the pandemic and its impact on our lives.

Faced with this crisis context, some companies, public organizations or even media, have gone in search of the best adapted solution to answer all our questions in emergency.

This is how the TF1 group launched its Chatbot in record time (less than a week), integrated in the full page of the LCI news channel’s website (Clustaar solution). With a capacity of more than 70 Questions-Answers, it allowed to cover the vast Covid-19 subjects worrying the Internet users and this, in a fast, precise and relevant way.

The content has continued to evolve and adapt to the changing times we live in.

Also, other initiatives are emerging involving the advent of intelligent instant messaging to closely match new uses.

Again with the support of the editor Clustaar, the French Government provides citizens with two “Messaging bot” on WhatsApp and Facebook Messenger, available 24/24h and 7/7d.

This project, which involves the publication of official information and health measures to be respected, has helped to limit the spread of “fake news”.

Less widespread but increasingly popular like the other channels, we find conversational agents also deployed in the form of “Callbot“.

This is the case of the Ministry of Solidarity and Health which, in co-construction with the editor Zaion, was able to satisfy the high demand arriving on their Covid-19 telephone line, providing answers to the most frequent FAQ type questions.

The objective of leaving no citizen unanswered was achieved with a deployment in less than 36 hours, while offering the possibility to speak to a human if needed!

In short, conversational agents have proven their efficiency and speed of deployment!
Fortunately, it’s not always about emergencies and pandemics.

Others took the plunge long before the crisis…

Mister Auto (PSA Group), a leader in the sale of automotive parts, is setting up a call bot called Matt, which can handle 30% of incoming calls to the customer service department, including order tracking.

This new generation conversational agent, powered by the AI of the ILIBOT by Viavoo platform, is able to understand and interpret the words of a person on the phone and provide answers or carry out related actions.

As the third largest electricity and gas operator in France, Total Direct Energie, a pioneer in innovation in customer relations, deployed a Chatbot named Jo in 2016, in addition to the LiveChat already online on the website since 2014.

In 5 years, Jo has gone from 300 to 2000 conversations per day in 2020, thanks in particular to a continuous optimization of its skills.

It can give text answers integrating content in some cases (images, video, tutorial …), redirect to pages, edit invoices and even transfer the conversation to a human agent via Livechat.

What will make your virtual agent successful


It’s simple: the Chat/Call or Voicebot that keeps all its promises is the one that gets the support of its end users, i.e. your customers or your employees (for internal use). In practice, we observe that the combination of human expertise and the performance of virtual agents with artificial intelligence guarantees a simplified customer experience and a unified path. The value proposition of hybridizing human and technology goes far beyond usage by widely impacting the entire organization, processes and businesses.

But then you will say to me, how to guarantee the success of such a project?
It is above all the good practices, the methodology used, the governance and the technology that will ensure the success of your project.

Here are some expert tips and questions to ask yourself:


Do not neglect the reflection phases before any start-up, a real guarantee of success if they have been well framed!

The framing phase will also have its importance in favor of co-creation and agility:

  • How to compose your project team and involve participants? (business, operational, IT customer service, marketing, …)
  • Definition of expectations, KPI’s, budget & timing
  • Specification & choice of the best adapted technological solution, while keeping in mind the scalability of the solution
  • Collaborative creative workshops, for a committed and efficient business team: What are your customer journeys? Which use cases should the virtual assistant focus on? What identity to give it (find a name, a graphic, a footprint,)

Change management & digital transition to take care of:

  • Training & Coaching of users and physical agents
  • Accompany its launch and enhance its benefits for the customer and for the teams.

Monitoring for continuous improvement:

  • Feed it with data, collect it regularly as it goes along, state it, label it, correct it so that the robot continues to learn and progress!

Of course, this list is still long and can be adapted to each project context, but the main thing to remember is that the deployment of a bot requires a few prerequisites! That’s why you should not hesitate to get help for one or all of these steps and thus have the best assets.

*(Source : Gartner (2018) cité dans Building the AI-powered customer center of the future by Customer Think (June 2018))