Added model files for sentiment

LICENSE.md

@@ -0,0 +1,15 @@
+# LICENSE
+
+                            SOFTWARE LICENSE AGREEMENT
+
+Copyright (c) 2024 Vincenzo Miracula. All Rights Reserved.
+
+By using this software, you agree to the following terms and conditions:
+
+1. You are granted a non-exclusive, non-transferable license to use this software for personal, non-commercial purposes only.
+2. You may not modify, distribute, or reverse-engineer the software.
+3. You may not sell, lease, sublicense, or otherwise transfer the software to any third party.
+4. This software is provided "as is" without any warranty, express or implied, including but not limited to the warranties of merchantability or fitness for a particular purpose.
+5. The copyright notice and this license agreement must be retained in all copies or substantial portions of the software.
+
+For further inquiries or permissions, please contact the copyright holder.

MANIFEST.in

@@ -0,0 +1,5 @@
+recursive-include GordonAI/models/sentiment *
+recursive-include GordonAI/models/emotion *
+recursive-include GordonAI/models/factchecker *
+include README.md
+include LICENSE

README.md

@@ -1,3 +1,78 @@
----
-license: cc-by-4.0
----
+# GordonAI
+
+GordonAI is an AI package designed for sentiment analysis, emotion detection, and fact-checking classification. The models are pre-trained on three languages: **Italian**, **English**, and **Spanish**. 
+
+## Features
+
+- **Sentiment Analysis**: Classifies text into three categories: **positive**, **negative**, and **neutral**.
+- **Emotion Detection**: Identifies the six basic emotions defined by Paul Ekman (1992): **joy**, **sadness**, **fear**, **anger**, **surprise**, **disgust** (plus **neutral**).
+- **Fact-Checking Classification**: Classifies text into **disinformation**, **hoax**, **fake news**, or **true news**.
+
+## Installation 
+
+You can install the package using `pip`. Simply run the following command:
+
+```bash
+pip install GordonAI
+```
+
+## Usage
+
+### Sentiment Analysis
+
+You can use the `SentimentAnalyzer` to predict the sentiment of a text. The analyzer classifies texts as positive, negative, or neutral.
+
+```python
+from GordonAI.models import SentimentAnalyzer
+# Initialize the sentiment analyzer
+analyzer = SentimentAnalyzer()
+# Predict sentiment of a list of texts
+result = analyzer.predict(["This is a great product!", "This is a terrible mistake."])
+# Output the predictions
+print(result)
+```
+
+### Emotion Detection
+
+You can use the `EmotionAnalyzer` to predict the emotion of a text. The analyzer classifies texts as joy, sadness, fear, anger, surprise, disgust or neutral.
+
+```python
+from GordonAI.models import EmotionAnalyzer
+# Initialize the emotion analyzer
+emotion_analyzer = EmotionAnalyzer()
+# Predict emotions of a list of texts
+result = emotion_analyzer.predict(["I'm so happy today!", "I'm feeling really sad."])
+# Output the predictions
+print(result)
+```
+
+### Fact-Checking Classification
+You can use the `FactAnalyzer`  to predict whether a texts or a claim falls into categories like disinformation, fake news, hoax, or true news.
+
+```python
+from GordonAI.models import FactAnalyzer
+# Initialize the emotion analyzer
+fact_analyzer  = FactAnalyzer()
+# Predict emotions of a list of texts
+result = fact_analyzer.predict(["This news story is about a real event.", "This news article is based on fake information."])
+# Output the predictions
+print(result)
+```
+
+## Requirements
+Python >= 3.9
+transformers
+torch
+
+You can install the dependencies using:
+```bash
+pip install transformers torch
+```
+
+## Acknowledgments
+
+This package is part of the work for my doctoral thesis. I would like to thank **NeoData** and **Università di Catania** for their valuable contributions to the development of this project.
+
+
+
+

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73082a4efd62700ff17fe9c218df11b7f7acda6c5359d5ba88cce0638ea5cd19
+size 1740308548

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}