Skip to content
NovaPulse — Sentiment Analysis Dashboard | Tacita.ai

Sentiment analysis of customer feedback

VerdeVita Cosmetics S.r.l., a cosmetics company, 85 employees, direct and e-commerce channels. 534 pieces of feedback gathered through AI interviews run with Tacita, average duration 3–5 minutes per interview. Analysis period: January–June 2025. Hybrid pipeline with a transformer classifier and aspect-based sentiment analysis.

534
Interviews completed
average duration 4.2 min
62%
Average sentiment score
+2.1pp vs previous half-year
+28
Estimated NPS
+4 points vs previous half-year

Positive rate

54%

289 interviews

Negative rate

22%

117 interviews

Sarcasm detected

4,9%

26 of 534 interviews

Average subjectivity

0,56

scale 0 (factual) – 1 (opinion)

Sentiment trend — 6 months

Monthly shift in the polarity of feedback gathered via Tacita

Positive
Neutral
Negative

Distribution of sentiment scores

Histogram of the scores assigned by the pipeline (0–100)

The concentration in the 55–80 band indicates overall positive sentiment. The cluster below 25 accounts for 7.8% of the interviews.

Estimated NPS — monthly trend

Net promoter score derived from interview sentiment

Interview volume — by month

Number of AI interviews completed through Tacita

Sentiment by specific aspect

The ABSA pipeline breaks each interview down into its constituent aspects and assigns an independent sentiment to each one. The model identifies 7 primary aspects for VerdeVita. Each interview touches on an average of 1.8 distinct aspects, for a total of 961 aspect mentions across the 534 interviews.

Sentiment–volume correlation by aspect

X axis = sentiment score. Y axis = number of mentions. Size = positive rate.

The aspects in the upper-left quadrant (low sentiment, high volume) require priority action. Price and returns are the two most critical areas.

68% of the interviews with a negative score contain at least two distinct emotions. Anger rarely appears on its own: in 64% of cases it comes with disappointment or frustration at an expectation that wasn't met.

Automated analysis — Plutchik emotion model, 534 interviews processed

Emotions, sarcasm and subjectivity

The sentiment score captures polarity. Emotional analysis goes further, identifying specific emotions according to Plutchik's 8-dimension model. The sarcasm detection module corrects false positives. Subjectivity analysis distinguishes factual answers from personal opinions.

Emotion map — Plutchik

Intensity detected vs cosmetics sector benchmark

VerdeVita
Benchmark

Sarcasm detection

Transformer classifier fine-tuned on an Italian dataset

Interviews containing sarcasm

26

of 534 in total (4.9%)


Classifier accuracy

F1 = 0,84

on a balanced internal test set


False positive rate

7,1%

neutral answers wrongly classified as sarcastic

Sarcasm inverts the polarity of an answer. The classifier detects typical lexical patterns such as hyperbole, apparent antithesis and incongruous superlatives. Sarcastic answers receive an automatic correction to their sentiment score.

Subjectivity analysis

Distribution of interviews by degree of subjectivity

Average subjectivity

0,56

scale 0 (factual) – 1 (opinion)


Factual answers (low subjectivity) mainly contain reports of defects or technical problems. Highly subjective ones express personal preferences. Telling the two categories apart improves the prioritization of operational action.

Who the interviewees are and when they answered

The 534 AI interviews with Tacita involved customers from different segments. Cross-analysis between segment and sentiment makes it possible to identify the groups with the most perceived problems.

Sentiment by customer segment

Interview volume, average sentiment and distribution by customer type

SegmentInterviewsSentimentAverage duration
Repeat customers18668%4.6 min
First purchase14255%3.8 min
E-commerce customers11848%4.1 min
Retail customers8872%3.4 min

Retail customers express the most positive sentiment (72%), probably linked to direct experience with the product. E-commerce customers show the most critical sentiment (48%), with complaints concentrated on shipping and returns.

Time heatmap — average sentiment

Day of the week on which the interviews were run. Hover for details.

Low
Medium
High

Sentiment by segment — distribution

Comparison of the positive/neutral/negative split for each segment

Extracts from the Tacita interviews

Each interview goes through 4 phases after transcription. Tokenization and preprocessing. Sentiment classification with a transformer model. Aspect extraction with ABSA. Sarcasm detection and subjectivity calculation. The result is a composite score that brings all the dimensions together.

The 4 phases of the pipeline

After the AI interview run with Tacita is transcribed (average duration 3–5 minutes), the text enters the analysis pipeline. The 4 phases are executed in sequence on each transcript.

01

Preprocessing

~0.2s per transcript

Tokenization, normalization, removal of conversational noise (interjections, false starts, repetitions). Handling of slang, abbreviations and Italian dialect variants gathered during the interviews.

02

Sentiment classification

~0.8s per transcript

Transformer model (fine-tuned RoBERTa-IT) with probabilistic output across 5 classes. Ensemble with weighted voting across 3 independent models to reduce the bias of any single classifier.

03

ABSA and emotional analysis

~1.2s per transcript

Aspect extraction with sequence labeling. Assignment of independent sentiment to each identified aspect. Emotion detection according to Plutchik's 8 primary dimensions.

04

Post-processing

~0.3s per transcript

Sarcasm detection with a dedicated classifier (F1 = 0.84). Subjectivity calculation. Automatic score correction for sarcastic answers. Generation of the final composite score.

How to read this dashboard

How is the feedback gathered?

The 534 pieces of feedback were gathered through conversational interviews run by a Tacita AI agent. Each interview lasts an average of 3–5 minutes and follows a semi-structured flow that leaves the customer room to express their views naturally, with no format constraints.

How is the sentiment score calculated?

The score is a weighted average of the results of three transformer models run in parallel. Each model produces a probability distribution across 5 classes (very negative, negative, neutral, positive, very positive). The final score is normalized on a 0–100 scale.

What sets ABSA apart from traditional sentiment analysis?

Traditional analysis assigns a single score to the whole interview. Aspect-based sentiment analysis breaks the transcript down into its constituent aspects and assigns a separate sentiment to each. An answer such as "the quality is excellent but the price is too high" produces two independent scores.

How does sarcasm detection work?

The classifier is a transformer model fine-tuned on a dataset of Italian texts annotated for sarcasm. It detects typical lexical patterns such as hyperbole, apparent antithesis and superlatives incongruous with the context. When an answer is classified as sarcastic, the sentiment score is inverted automatically.

What does the subjectivity index indicate?

The index measures how far an answer expresses a personal opinion (high value) rather than a factual observation (low value). Factual answers often contain reports of bugs, defects or logistics problems. Highly subjective ones express preferences. The distinction helps separate technical problems from perceptions.

GP

Data handling and privacy. Tacita interview transcripts are anonymized before analysis. No personal data is retained in the training dataset. The infrastructure is GDPR compliant (art. 6.1.f — legitimate interest in improving the service). Anonymized transcripts are kept for 12 months and then deleted.

Want to apply this analysis to your own data?

Tacita's AI interviews gather structured feedback in 3–5 minutes. The pipeline adapts to any sector.

Talk to the team