files added

TBModel/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "vinai/bertweet-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertweetTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

TBModel/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeaab45505d70a0b9ac82575b41bbbc81a758d4ee164500bb9943cf5beafab09
+size 539679413

TBTokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

TBTokenizer/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

TBTokenizer/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "normalization": true,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BertweetTokenizer",
+  "unk_token": "<unk>"
+}

analyze.py

@@ -0,0 +1,94 @@
+import streamlit as st
+import pandas as pd
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import emoji
+
+model_path = "ANLPRL/TBModel"
+tokenizer_path = "ANLPRL/TBTokenizer"
+
+# Load the tokenizer and model
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(tokenizer_path)
+
+def predict(text):
+    encoded_data = tokenizer.encode_plus(text, padding=True, truncation=True, return_tensors='pt')
+    input_ids = encoded_data['input_ids']
+    attention_mask = encoded_data['attention_mask']
+    with torch.no_grad():
+        outputs = model(input_ids, attention_mask)
+    logits = outputs.logits
+    probabilities = torch.softmax(logits, dim=1)
+    _, predicted = torch.max(probabilities, dim=1)
+    
+    # Create dictionary to map numerical labels to categories
+    label_dict = {0: 'Positive', 1: 'Negative', 2: 'Neutral'}
+    predicted_label = label_dict[predicted.item()]
+    
+    return predicted_label
+
+# Define examples as a list
+examples = [
+    "ChatGPT Plus uses cutting-edge AI technology to learn from customer conversations.",
+    "ChatGPT can produce harmful and biased answers.",
+    "Gpt dont have feelings or a personal identity, but it strive to provide informative responses.",
+]
+
+# Create the Streamlit app
+emoji_dict = {
+    "positive": "\U0001F60A",
+    "negative": "\U0001F61E",
+    "neutral": "\U0001F610"
+}
+
+st.title("CHAT-GPT SENTIMENT ANALYSIS")
+
+# Create the form to handle user inputs
+with st.form("sentiment_analysis_form"):
+    # Add the dropdown list for examples
+    selected_option = st.selectbox("Select an example to analyze", [""] + examples, index=0)
+
+    # Add the text input for user input
+    user_input = st.text_input("Enter your own text to analyze", "")
+
+    # Define color codes for different sentiment classes
+    positive_color = "#00C851"
+    negative_color = "#ff4444"
+    neutral_color = "#FFBB33"
+
+    # Add the submit button to analyze the sentiment
+    analyze_button = st.form_submit_button("Analyze")
+
+# Handle the form submission
+if analyze_button:
+    if user_input.strip() != "":
+        prediction = predict(user_input.strip())
+        if prediction == 'Positive':
+            st.write(f"<span style='color:{positive_color}; font-weight:bold;'>{emoji_dict['positive']} Positive</span>", unsafe_allow_html=True)
+        elif prediction == 'Negative':
+            st.write(f"<span style='color:{negative_color}; font-weight:bold;'>{emoji_dict['negative']} Negative</span>", unsafe_allow_html=True)
+        else:
+            st.write(f"<span style='color:{neutral_color}; font-weight:bold;'>{emoji_dict['neutral']} Neutral</span>", unsafe_allow_html=True)
+    elif selected_option != "":
+        prediction = predict(selected_option)
+        if prediction == 'Positive':
+            st.write(f"<span style='color:{positive_color}; font-weight:bold;'>{emoji_dict['positive']} Positive</span>", unsafe_allow_html=True)
+        elif prediction == 'Negative':
+            st.write(f"<span style='color:{negative_color}; font-weight:bold;'>{emoji_dict['negative']} Negative</span>", unsafe_allow_html=True)
+        else:
+            st.write(f"<span style='color:{neutral_color}; font-weight:bold;'>{emoji_dict['neutral']} Neutral</span>", unsafe_allow_html=True)
+    else:
+        st.write("Please enter a text or select an example to predict")
+
+
+st.markdown("""---""")
+st.caption("""
+    Developed by Applied NLP Research Lab
+School of Digital Sciences,
+Kerala University of Digital Sciences, Innovation and Technology,
+Technopark phase 4, Thiruvananthapuram, India | 
+Email: [email protected]   
+    <span style='text-align:center; display:block;'>
+        https://sites.google.com/duk.ac.in/anlprl
+    </span>
+""", unsafe_allow_html=True)

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+pandas
+torch
+transformers
+emoji