Detecting Human Emotions Using Machine Learning Techniques: A Comprehensive Approach
Bibliographic record
Abstract
The ability to comprehend and respond to human emotions is a key component of effective interaction, yet it remains an obstacle in artificial intelligence. With speech interactions becoming increasingly common in everyday life, machines that can analyze emotions behind spoken words offer significant potential across various fields. The proposed research develops an innovative system which merges speech-to-text processing with emotion detection from transcribed speech to allow machines to interpret human emotions through spoken words. The dual-stage framework undergoes testing through various machine learning and deep learning approaches (sadness, joy, love, anger, fear, and surprise) to assess the effectiveness of various machine learning and deep learning algorithms. Moreover, it aims to simulate human-like emotional interpretation by developing a machine learning model using Natural Language Processing and Long Short-Term Memory. This approach is effective for analyzing text and speech, as it can process sequential data, helping to identify emotions expressed in spoken language. This research aims to develop solutions that improve human-computer interactions across various domains. Speech is transcribed using speech recognition tools and then for this text we use a range of machine learning and deep learning algorithms, including Naive Bayes, K-Nearest Neighbors, Logistic Regression, Support Vector Machines, Decision Trees, Random Forests, and Long Short-Term Memory, to build multiple models. These models are then tested on a separate dataset, and their performance compared. The insights gained from analyzing residents' emotional expressions could contribute to enhancing the safety of smart home systems especially for elderly or disabled people where we can get their emotions through their spoken words.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".