Using a TOPSIS Method to Evaluate and Select AI Chatbots for Improving Customer Service Communication
Bibliographic record
Abstract
Chatbot has become an innovation for business to connect with customers. People can communicate with technology devices in the same way they would with real people through Chatbots. Traditional Chatbots typically depend on already programmed principles and replies, while AI (artificial intelligence) Chatbots comprehend and dynamically respond to user inquiries utilizing natural language processing (NLP) and machine learning (ML). Chatbots powered by AI have an increased requirement to communicate with customers in a fast and effective way. People can communicate with technology devices like they were speaking to a real person, which are software programs that simulate human conversation which can be texts or speeches. Many criteria quantitative criteria, including frequently asked questions (FAQs), security, brands, improving efficiency, and enhancing engagement, etc., and quantitative criteria, including cost, bot analytics built-in templates and customer relationship management (CRM), etc., need to be considered when evaluating AI Chatbots for companies to enhance customer service. Moreover, criteria may have different importance. Therefore, evaluating AI Chatbots is a MCDM (multiple criteria decision making) problem. Many companies do not know how to select the most suitable one to serve their customers. To address this issue, the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), one of MCDM approaches, is used to evaluate AI Chatbots; and criteria weights will be produced by applying BWM (Best Worse Method). A numerical example will be used to present feasibility of the used method, and a comparison will be conducted to display its effectiveness.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".