Telugu Sentiment Summary Engine

@glanegonsalves

Hey there Glane here, hope you're doing well. I can help you in doing sentiment analysis using Python on your telugu texts. Feel free to get in touch.

@JaibhanSinghGaur

Hi, I can build a Python-based Telugu sentiment analysis pipeline that generates one-line summaries and classifies reviews as Positive, Negative, or Neutral, returning clean JSON output. I’ll use a hybrid approach (pretrained Telugu models + rule-based cues) for better accuracy, and provide the model, code, README, and a validation report meeting the required F1 score. Ready to start.

@dushyant317

Hello, I’ve carefully reviewed your project requirements and clearly understand the tasks involved. I have 13 years of experience and strong expertise in the exact skills this project requires. I have successfully delivered similar projects before and can share relevant samples if needed. I will complete this within your expected timeline while maintaining quality and clear communication. I look forward to working with you and contributing sincerely to your project’s success.

@thakurharshh

Hello, I can build an end-to-end Telugu sentiment analysis and one-line summary pipeline with clean JSON output per record. • Ingest raw Telugu customer reviews • Generate concise one-line summaries • Classify sentiment as Positive, Negative, or Neutral • Use a hybrid approach combining lexicon-based rules with a fine-tuned ML / transformer model (e.g., Telugu-BERT / FastText) • Deliver trained model files, versioned lexicons, and a clear README The solution will be fully reproducible, easy to retrain, and evaluated with precision, recall, and F1 score on a held-out dataset. Ready to start immediately and iterate based on your sample data. Regards, Harsh

@rajaa151

I can deliver an end-to-end hybrid NLP pipeline for Telugu customer reviews that produces concise one-line summaries and accurate sentiment labels (Positive/Negative/Neutral) in clean JSON format. My approach blends rule-based linguistic cues (custom Telugu sentiment lexicons, idiomatic patterns, negation handling) with a fine-tuned transformer model (Telugu-BERT / IndicBERT), optionally enhanced with FastText embeddings for robustness on low-resource or noisy text. Deliverables will include a fully reproducible Python/notebook pipeline, trained model files with versioning, custom dictionaries, and a clear README covering setup, retraining, and updates. I will also provide a validation report (precision, recall, F1, accuracy) on a held-out domain-matched test set, targeting F1 ≥ 0.80 while ensuring summaries remain faithful and readable.

@samsungm3

Hello, I can deliver the complete Telugu sentiment analysis and summarization pipeline as described. The solution will automatically process Telugu customer reviews, generate a clear one-line summary, and classify sentiment as Positive, Negative, or Neutral, with clean JSON output for each record. I will use a hybrid approach combining rule-based Telugu sentiment cues (negations, intensifiers, common idioms) with a machine-learning model based on pretrained Indic/Telugu transformers to ensure good accuracy. The pipeline will be implemented in Python and will run end-to-end on your dataset. Deliverables will include: - Python script/notebook for full processing - JSON output per review (summary + sentiment) - Trained model files and any custom lexicons - README with setup, usage, and retraining steps - Validation metrics (precision, recall, F1 score) I am bidding ₹15,000 for the complete project and can deliver within 5 days. I am open to feedback and small adjustments to meet your expectations. Thank you for considering my proposal.

@baskarrajendran

Hello, this is a very interesting NLP project and I’m curious to work on Telugu sentiment and summary together with strong accuracy. I can build a hybrid pipeline that combines rule-based Telugu lexicon signals with a machine-learning model like Telugu-BERT or multilingual transformers to classify each review as Positive, Negative, or Neutral and also generate a clear one-line summary that keeps the main meaning of the review. Approach: • Clean and normalize Telugu text • Apply custom sentiment lexicon and idiom rules • Use fine-tuned transformer or FastText for final sentiment prediction • Generate short extractive or light abstractive summaries • Output clean JSON per review Deliverables: • Python script or notebook that runs end-to-end on your data • Trained model files and custom Telugu lexicon with version control • README with setup, dependencies, and retraining steps • Validation report with precision, recall, F1, and accuracy I will tune the model on your domain data and target F1 score above 0.80 as requested. I also focus on making the pipeline easy to update when new reviews are added, so retraining will not be complex. I have experience with NLP pipelines, transformers, dataset preparation, and evaluation metrics, and I pay strong attention to real-world language issues like spelling variations and informal Telugu usage.

@vamsi367

I have strong experience building Python data pipelines and automated processing systems. I’m familiar with NLP fundamentals and can implement a solution that ingests raw Telugu text, generates concise summaries, and classifies sentiment using a hybrid approach (rule-based + ML). I will deliver a Python script, models, JSON output, and documentation.