diff --git a/.gitignore b/.gitignore
index ca2b75a..3fa3a99 100644
--- a/.gitignore
+++ b/.gitignore
@@ -2,9 +2,9 @@
 __pycache__/
 *.pyc
 *.jsonl
+*.json
 *.code-workspace
 .env
-topic_buckets.txt
 
 # React App Vite
 node_modules/
diff --git a/server/app.py b/server/app.py
index 48e757a..7e062b9 100644
--- a/server/app.py
+++ b/server/app.py
@@ -4,6 +4,7 @@ from server.stat_gen import StatGen
 
 import pandas as pd
 import traceback
+import json
 
 app = Flask(__name__)
 
@@ -13,7 +14,8 @@ CORS(app, resources={r"/*": {"origins": "http://localhost:5173"}})
 # Global State
 posts_df = pd.read_json('posts.jsonl', lines=True)
 comments_df = pd.read_json('comments.jsonl', lines=True)
-domain_topics = open("topic_buckets.txt").read().splitlines()
+with open("topic_buckets.json", "r", encoding="utf-8") as f:
+    domain_topics = json.load(f)
 stat_obj = StatGen(posts_df, comments_df, domain_topics)
 
 @app.route('/upload', methods=['POST'])
@@ -28,15 +30,15 @@ def upload_data():
     if post_file.filename == "" or comment_file.filename == "" or topic_file == "":
         return jsonify({"error": "Empty filename"}), 400
 
-    if not post_file.filename.endswith('.jsonl') or not comment_file.filename.endswith('.jsonl') or not topic_file.endswith('.txt'):
-        return jsonify({"error": "Invalid file type. Only .jsonl and .txt files are allowed."}), 400
+    if not post_file.filename.endswith('.jsonl') or not comment_file.filename.endswith('.jsonl') or not topic_file.endswith('.json'):
+        return jsonify({"error": "Invalid file type. Only .jsonl and .json files are allowed."}), 400
     
     try:
         global stat_obj
 
         posts_df = pd.read_json(post_file, lines=True)
         comments_df = pd.read_json(comment_file, lines=True)
-        stat_obj = StatGen(posts_df, comments_df, topic_file.splitlines())
+        stat_obj = StatGen(posts_df, comments_df, json.load(topic_file))
         return jsonify({"message": "File uploaded successfully", "event_count": len(stat_obj.df)}), 200
     except ValueError as e:
         return jsonify({"error": f"Failed to read JSONL file: {str(e)}"}), 400
diff --git a/server/nlp.py b/server/nlp.py
index d5a04f3..dbc9021 100644
--- a/server/nlp.py
+++ b/server/nlp.py
@@ -1,13 +1,12 @@
 import torch
 import pandas as pd
-import numpy as np
 
 from transformers import pipeline
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 
 
-model = SentenceTransformer("all-MiniLM-L6-v2", device=0 if torch.cuda.is_available() else 1)
+model = SentenceTransformer("all-mpnet-base-v2", device=0 if torch.cuda.is_available() else 1)
 
 def add_emotion_cols(
         df: pd.DataFrame, 
@@ -38,16 +37,28 @@ def add_emotion_cols(
 
 def add_topic_col(
         df: pd.DataFrame,
+        title_col: str,
         content_col: str,
-        domain_topics: list[str],
-        confidence_threshold: float = 0.15
+        domain_topics: dict,
+        confidence_threshold: float = 0.20
     ) -> None:
+
+    topic_labels = list(domain_topics.keys())
+    topic_texts = list(domain_topics.values())
+
     topic_embeddings = model.encode(
-        domain_topics,
+        topic_texts,
         normalize_embeddings=True,
     )
 
-    texts = df[content_col].astype(str).tolist()
+    titles = df[title_col].fillna("").astype(str)
+    contents = df[content_col].fillna("").astype(str)
+
+    texts = [
+        f"{title}. {content}" if title else content
+        for title, content in zip(titles, contents)
+    ]
+
     text_embeddings = model.encode(
         texts,
         normalize_embeddings=True,
@@ -60,8 +71,9 @@ def add_topic_col(
     best_idx = sims.argmax(axis=1)
     best_score = sims.max(axis=1)
 
-    df["topic"] = [domain_topics[i] for i in best_idx]
+    df["topic"] = [topic_labels[i] for i in best_idx]
     df["topic_confidence"] = best_score
+
     df.loc[df["topic_confidence"] < confidence_threshold, "topic"] = "Misc"
 
     return df
\ No newline at end of file
diff --git a/server/stat_gen.py b/server/stat_gen.py
index d2beed6..35abb08 100644
--- a/server/stat_gen.py
+++ b/server/stat_gen.py
@@ -42,7 +42,7 @@ class StatGen:
         df["weekday"] = df["dt"].dt.day_name()
         
         add_emotion_cols(df, "content")
-        add_topic_col(df, "content", self.domain_topics)
+        add_topic_col(df, "title", "content", self.domain_topics)
 
     def _tokenize(self, text: str):
         tokens = re.findall(r"\b[a-z]{3,}\b", text)