polish remarks

jieyima · Mar 14, 2018 · e2ff06b · e2ff06b
1 parent fe882c9
commit e2ff06b
Showing 1 changed file with 13 additions and 5 deletions.
diff --git a/NLP_AWS_SouthPark.ipynb b/NLP_AWS_SouthPark.ipynb
@@ -12,7 +12,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "In this notebook, I used Amazon comprehend to implement sentiment analysis on one review of the episode of South Park from Dani Di Placido Forbes **#OnTV** section. "
+    "In this notebook, I used Amazon comprehend to implement sentiment analysis on one review of the episode of South Park from Dani Di Placido Forbes **#OnTV** section (published Nov. 9, 2017). "
    ]
   },
   {
@@ -160,12 +160,13 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Seems that the review for Garrison Trump in this episode is mostly neative (a dominant proportion of 53%), and somewhat netural (41%). \n",
+    "**Seems that the review for Garrison Trump in this episode is mostly negative (a dominant proportion of 53%), and somewhat neutral (41%).**\n",
     "\n",
-    "The result is not surprising, as in this episode President Garrison keeps on his campaign promise to \"fxxk them all to death\", and threaten those who against him. "
+    "**The result is not surprising, as in this episode President Garrison keeps on his campaign promise to \"fxxk them all to death\", and threaten those who against him.** "
    ]
   },
   {
@@ -192,7 +193,7 @@
    },
    "outputs": [],
    "source": [
-    "path = \"/Users/Jessica/Desktop/BAX452/Natural_Language_Processing/SouthParkReview.txt\"\n",
+    "path = \"~/Natural_Language_Processing/SouthParkReview.txt\"\n",
     "doc1 = open(path, \"r\")\n",
     "output = doc1.readlines()"
    ]
@@ -201,7 +202,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "     -- Note: there is a text size limit for Detectsemtiment analysis in AWS of 5000 bytes. So I have to manually cut down the text file and make the size fit. "
+    "     Author Note: there is a text size limit for Detectsemtiment analysis in AWS of 5000 bytes. So I have to manually cut down the text file and make the size fit."
    ]
   },
   {
@@ -261,6 +262,13 @@
     "print(json.dumps(comprehend.detect_sentiment(Text=output[1], LanguageCode='en'), sort_keys=True, indent=4))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**The review for this episode is neutral (a dominant proportion of 69%) to positive (30%). Key word 'favorite' contributes mostly to the positive sentiment.**"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},