Sentiment Analysis Of MLM Company Consulting Satisfaction Using The Support Vector Machine (SVM) Method

Feb 27, 2025 by ADMIN 104 views

**Revealing MLM Consultant Satisfaction: Sentiment Analysis with Support Vector Machine Method**

Introduction

The Multi Level Marketing (MLM) business in Indonesia has experienced rapid growth, but it is often shrouded in a negative stigma about "money games" and imbalances in advantage, making many people hesitant to join. This has led to the emergence of two groups of consultants: active and passive. Passive consultants often choose to exit due to various obstacles and dissatisfaction. Public opinion on MLM becomes crucial as it can affect the company's image and public trust. Therefore, this study aims to analyze the sentiment of MLM consultant satisfaction using the Support Vector Machine (SVM) method.

Background

The MLM business has been a significant contributor to the Indonesian economy, providing opportunities for individuals to earn a living through the sale of products or services. However, the industry has also faced criticism and controversy, with many people viewing it as a "money game" that prioritizes recruitment over product sales. This negative perception has led to a decline in public trust and confidence in the industry.

Methodology

This study used a dataset of 10,000 documents obtained from a questionnaire given to MLM consultants. The data was processed through a series of steps, including:

Case folding: converting all text to lowercase to reduce the dimensionality of the data.
Tokenization: breaking down the text into individual words or tokens.
Filtering stopwords: removing common words such as "the," "and," and "a" that do not add much value to the meaning of the text.
Stemming: reducing words to their base form to reduce the dimensionality of the data.

The weighting of words was done using the TF-IdF (Term Frequency-Inverse Document Frequency) method, which takes into account the frequency of a word in a document and its rarity across the entire dataset.

Sentiment Analysis using SVM

The SVM method was then applied to conduct sentiment analysis on the preprocessed data. The SVM algorithm is a type of supervised learning algorithm that can be used for classification tasks. In this study, the SVM algorithm was trained on a labeled dataset of positive and negative sentiments to learn the patterns and relationships between the words and their corresponding sentiments.

The results of the sentiment analysis showed an accuracy of 82%, indicating that the SVM method was effective in classifying the sentiments of the MLM consultants.

Benefits of Sentiment Analysis

Sentiment analysis provides several benefits to MLM companies, including:

Increasing consumer confidence

Understanding and responding to negative sentiments from consultants can help companies build trust and positive images in the eyes of the community.

Improving business strategies

Sentiment analysis can identify areas that need to be improved, such as compensation, training, and support programs for consultants.

Making better business decisions

Sentiment data can provide guidance for making strategic decisions such as product development, marketing programs, and consulting retention strategies.

The Importance of the SVM Method

The SVM method is an effective machine learning algorithm for sentiment analysis due to its ability to classify data into positive, negative, or neutral categories with a high level of accuracy. Additionally, SVM can handle data with high dimensions, making it ideal for complex text analysis.

Conclusion

Sentiment analysis of MLM consulting satisfaction using the SVM method has proven effective in revealing consumer perceptions and opinion. This information can be a valuable tool for MLM companies to improve performance, build trust, and achieve success in the long run. By understanding the sentiments of their consultants, MLM companies can make informed decisions to improve their business strategies and build a positive image in the eyes of the community.

Future Research Directions

This study has several limitations, including the use of a small dataset and the reliance on a single machine learning algorithm. Future research can build on this study by:

Using a larger dataset: collecting more data from a wider range of sources to improve the accuracy of the sentiment analysis.
Using multiple machine learning algorithms: comparing the performance of different machine learning algorithms to determine which one is most effective for sentiment analysis.
Analyzing sentiment over time: examining how sentiment changes over time to identify trends and patterns in consumer perception.

By addressing these limitations and expanding on this study, future research can provide a more comprehensive understanding of the sentiments of MLM consultants and the effectiveness of the SVM method in sentiment analysis.

Q: What is the purpose of this study?

A: The purpose of this study is to analyze the sentiment of MLM consultant satisfaction using the Support Vector Machine (SVM) method. The goal is to provide a deeper understanding of the level of consultant satisfaction with MLM companies and to identify areas for improvement.

Q: What is the significance of sentiment analysis in the MLM industry?

A: Sentiment analysis is crucial in the MLM industry as it can help companies understand the perceptions and opinions of their consultants, which can affect the company's image and public trust. By analyzing sentiment, MLM companies can make informed decisions to improve their business strategies and build a positive image in the eyes of the community.

Q: What is the SVM method, and how does it work?

A: The SVM method is a type of supervised learning algorithm that can be used for classification tasks. In this study, the SVM algorithm was trained on a labeled dataset of positive and negative sentiments to learn the patterns and relationships between the words and their corresponding sentiments. The SVM method is effective in classifying data into positive, negative, or neutral categories with a high level of accuracy.

Q: What are the benefits of using the SVM method for sentiment analysis?

A: The SVM method has several benefits, including:

High accuracy: The SVM method can classify data with high accuracy, making it an effective tool for sentiment analysis.
Handling high-dimensional data: The SVM method can handle data with high dimensions, making it ideal for complex text analysis.
Flexibility: The SVM method can be used for various classification tasks, including sentiment analysis.

Q: What are the limitations of this study?

A: This study has several limitations, including:

Small dataset: The study used a small dataset, which may not be representative of the entire MLM industry.
Reliance on a single machine learning algorithm: The study relied on a single machine learning algorithm, which may not be the most effective tool for sentiment analysis.
Limited analysis: The study only analyzed sentiment at a single point in time, which may not capture changes in sentiment over time.

Q: What are the future research directions for this study?

A: Future research can build on this study by:

Using a larger dataset: Collecting more data from a wider range of sources to improve the accuracy of the sentiment analysis.
Using multiple machine learning algorithms: Comparing the performance of different machine learning algorithms to determine which one is most effective for sentiment analysis.
Analyzing sentiment over time: Examining how sentiment changes over time to identify trends and patterns in consumer perception.

Q: How can MLM companies use the results of this study?

A: MLM companies can use the results of this study to:

Improve business strategies: Identifying areas for improvement, such as compensation, training, and support programs for consultants.
Build trust: Understanding and responding to negative sentiments from consultants to build trust and a positive image in the eyes of the community.
Make informed decisions: Using sentiment data to guide strategic decisions, such as product development, marketing programs, and consulting retention strategies.

Q: What are the implications of this study for the MLM industry?

A: This study has several implications for the MLM industry, including:

Increased focus on consultant satisfaction: MLM companies may need to prioritize consultant satisfaction to improve their business strategies and build trust.
Improved communication: MLM companies may need to improve communication with their consultants to understand their perceptions and opinions.
Increased transparency: MLM companies may need to increase transparency in their business practices to build trust and a positive image in the eyes of the community.