Skip links

Voice of customer (VOC) analysis SOLUTION

Methods to optimize business and customer satisfaction

Saltlux technology


Saltlux Technology - phân tích tiếng nói khách hàng voc - voice of customer

What is Voice of Customer?

VOC (Voice Of Customer) refers to various queries, complaints, suggestions, etc. that reflect customer reactions to companies’ services and their management activities. The data comprising the VOC has traditionally been consulting memos of consultants obtained through CRM’s customer support system used mainly at call centers and bulletin boards for customer support. However, now it has grown to include comprehensive data such as customers’ reactions to services and products obtained through various channels including blogs, Twitter, community sites, and other forms.

What is Saltlux Technology's VOC analysis service?

Voice of Customer (VOC) analysis solution by Saltlux uses a self-developed VOC system to collect internal/external informal VOC information, then analyze the collected information and provide the analyzed information on the web. The solution builds consulting record analysis systems by using data collection/analysis solutions such as text mining and related information searches of which functions are optimized.

Saltlux Technology - phân tích tiếng nói khách hàng voc - voice of customer


Collects and integrates with real-time VOC from various channels, such as consulting memos at the Customer Center, email, social media, and portal bulletin boards.


Perform in-depth analysis of customer complaints and comments, detect abnormalities early, and provide a real-time feedback system.

Our Voice of Customer (VOC) analysis service collects and integrates with real-time VOC from various channels, then performs in-depth analysis of customer complaints and comments, detects abnormalities early, and provides a real-time feedback system.

Saltlux Technology - phân tích tiếng nói khách hàng voc - voice of customer

Why choose our Voice of Customer (VOC) analysis service?

Saltlux Technology

Respond to customer complaints

Solutions to customers' growing need to be understood and responded to complaints and opinions that are appearing more frequently in multi-channels and are gradually becoming harder to collect and understand.

Solve potential risks

Detecting and providing a real-time response system to reviews and complaints about products/services in the media that are likely to become future risks.

Improve business efficiency

Maximize customer satisfaction, manage reputation, manage risk in real time, and plan new business by deeply analyzing data collected from a variety of channels.

Effective feedback from consultant

Help consultants effectively respond to different customer channels. Quickly and accurately capture customer requests and feedbacks.

Increase the management efficiency of the manager

Enhance the efficiency of the customer service system and the management performance of the manager.

Increase sales

Increase sales by enhancing customer satisfaction through effective and timely responds.

Where do we collect the voice of customers?

VOC Inside

Customer voice is received by Corporate Internal CS Channels (VOC channels) within the enterprise such as CTI, ERMS, chat, self-service system,...

01 01

VOC Outside

VOC related to the company spreading in the external environments of companies. Collection and monitoring of outside VOC are more difficult than the inside VOC.

02 02

VOC Online

Collect customer opinions over the internet, from websites to social networks.

03 03

VOC Offline

Voice of customers are collected from offline channels such as direct consultation, fax, phone, mail, etc.

04 04

implementation process

Discovery/Selection of the analyze topics

Professional personnel to discover and select subjects that are the most effective in analyzing customer needs.

Collection of informal text data

Validated solutions that are able to regularly collect and analyze needed informal text data.

Informal text data language processing

Increase data accuracy through language processing of informal text data.

VOC data classification

Automatic classification solutions that are able to filter and classify collected information.

Informal VOC data analysis

Analysis of trends and correlation between VOCs.

Visualization and Dashboard

Visualization of VOC analysis results using various statistical methods and Dashboard.


Informal VOC Data-Related Information Analysis

By applying topic clustering technology, it connects all internal and external related knowledge and discloses the correlation to provide users with insights.

It verifies related issues occurring around issues by showing correlations and expressing major-related keywords by radar charts.

Visualization of Statistical Information

By quantifying the possibility of issue occurrence, it correctly understands the causes of issues and establishes countermeasures via visualization and dashboards. It analyzes property information by classifying collected consulting information of customers in various statistical methods (frequency, development, and multi-dimensional analysis).

Analysis of Related Issues

It inquiries for related issues about internal and external collected information (Twitter, blogs, cafes, etc.) and provides trends analysis.
1. Inquiry for ranking of keywords related to interest keywords.
2. Status of occurrence of related keywords by period.
3. Ranking by related keyword.
4. Inquiry for the status of collected data information.

General Dashboard

It can view customer demands at once by providing recent trends of VOC in various formats such as period, age, sex, etc.

Informal VOC Data Trends Analysis

Provide services by conducting regular statistical analysis of interest terms within the relevant domain through trend analyses.

Extract popular terms to extract frequently mentioned words in the analysis cycle and extraction of sharply increasing terms reflected by the rising tendency of the frequency mentioned in the past based on the analysis time.

Multidimensional analysis

Support analysis by classification of the trend analysis of a variety of items.

Information classification

Classification of information by consultant, analysis time, type of consultant, customer characteristics, collection channel, consulting information attributes.

Trend analysis

Conduct a fundamental analysis of the status of each item, over time using an analysis function that shows trends over the time course of each item. At the same time, provide analysis results in different tabular formats.

Frequency Analysis

Provide analyzed information by frequency and period for each item regarding featured information.

Provide analysis results through various types of graphs and tables.


It provides various types of high visibility reports and statistics regarding analyzed VOC.
1. Status requests include keywords by type such as customer demand, service, treatment result, etc.
2. Enter multiple keywords when inquiring about types.
3. Enter exclusion keywords while searching the results.
4. Inquiry for setting the period.

Comprehensive Ranking of Keywords

Verify continuous VOC issues through comprehensive rankings, understand new emerging issues through sharply increasing rankings, and provide interest keyword rankings to show how the information consumers desire is ranked.
1. Inquiry for issue keywords by type (customer/demand/service).
2. Development of related keywords about question keywords.
3. Inquiry for the best issue keyword results during the relevant period.
4. Inquiry for the search results of question keywords.


Generally, VOC data has the following content characteristics with each characteristic needs to be applied a suitable analysis technique.

Short text compared to general documents

A consulting memo is written with short content of 100 characters on average. In some cases, it is not a sentence, but rather an enumeration of keywords about main issues (complaints, defects, etc.).

May include sensitive information

When describing consulting contents with customers as they are, it includes various customer information such as name, address, resident registration number, telephone number, card number, etc. Such private information is not exposed to the analysis results, instead, it is filtered through a preprocessing process.

Description with abbreviation and a colloquial style

VOC data, which is built by counselors at call centers, is prepared during the short consulting time with customers. As a result, it is often written with abbreviations and colloquial styles for the counselors’ convenience. It is needed to consider that such abbreviations and colloquial styles can be effectively processed in the language analysis phase.

Subordination of product/service domain

VOC data is generated from customer-facing management activities such as sales of products and services. Therefore, VOC data includes feedback such as customers’ various complaints, suggestions, and opinions about products and services. It is necessary to secure and build keywords such as product names, service names, customer classification, etc. that can represent domain knowledge about products and services.

Applying partial standardization

In the effort to use contents within call centers, partially standardized patterns can be stored. However, in reality, it is difficult to conduct pattern-based analysis without exception, as there are many data errors due to various customer feedbacks and rapid personnel replacement of call centers. Therefore, it should process parts described with patterns and other data.

Analysis Technique
of VOC Data

Provide a ranking form by measuring the order of issued vocabularies by period (hourly, daily, weekly, and more) and measuring the generation of meaningful vocabularies (noun, noun phrase) in the document clusters. The technology used is Term Frequency-based statistical analysis by period.

Express related vocabularies through flash-type visualization by analyzing relationships between vocabularies. Technologies used are Topic rank language analyzer and characteristic extraction.

Change of certain vocabularies according to time elapse. The technology used is the visualization of Term Frequency changing trend analysis (line charts, bar graphs, and more)

Automatic classification into good/bad by analyzing customer opinions (consulting memos, bulletin board posting, and more). The technology used is classification based on pattern matching of language analyzers (predicate analysis).

It is necessary to verify VOC data that will be analyzed and shared with customers. Even if the customer realized that the quality of the VOC data was poor, they are likely to overlook content issues after the project was completed.

It is necessary to prepare a detailed customer demand scenario from which information is ultimately extracted from VOC to analyze. Without this, the risk will increase over the time spent discussing a project.

Saltlux Technology
Saltlux Technology - phân tích tiếng nói khách hàng voc - voice of customer
Saltlux Technology
Saltlux Technology - phân tích tiếng nói khách hàng voc - voice of customer

Engine screen

This website uses cookies to improve your web experience.