ABSTRAT:

In recent times, sentiment analysis in low resourced languages and regional languages has become emerging areas in natural language processing. Researchers have shown greater interest towards analysing sentiment in Indian languages such as Hindi, Telugu, Tamil, Bengali, Malayalam, etc. In best of our knowledge, microscopic work has been reported till date towards Indian languages due to lack of annotated data set. In this paper, we proposed a two-phase sentiment analysis for Telugu news sentences using Telugu Sent WordNet. Initially, it identifies subjectivity classification where sentences are classified as subjective or objective. Objective sentences are treated as neutral sentiment as they don’t carry any sentiment value. Next, Sentiment Classification has been done where the subjective sentences are further classified into positive and negative sentences. With the existing Telugu Sent WordNet, our proposed system attains an accuracy of 74% and 81% for subjectivity and sentiment classification respectively

EXISTING SYSTEM :

In the recent past, researchers have shown their interest towards sentiment analysis in the context of Indian languages such as Hindi, Bengali, Telugu, Punjabi, Marathi, etc. [9–20]. Das and Bandyopadhyay [9] deployed a computational technique on English sentiment lexicons and English-Bengali bilingual dictionary to developed a Bengali Sent WordNet. In their subsequent work [10], they have extended their work and added two more Indian languages such as Hindi and Telugu to the Sent WordNet through an interactive gaming strategy called “ Dr.Sentiment” to create and validate the Sent Word- Net(s) for three Indian languages with the help of Internet users. In this game, they considered Sentimentality analysis based on concept-culture wise, age wise and gender wise. Further, they have used this Sent WordNet to predict the polarity of a word and also suggested four approaches namely, the dictionary based, WordNet-based, corpus-based and inter- active game (Dr.Sentiment) [11] to increase the coverage of generated Sent WordNet. In dictionary-based approach, they have developed a bilingual dictionary for English and Indian languages. In the Wordnet-based approach, they expanded the WordNet using synonym and antonym relations

EXISTING SYSTEM DISADVANTAGES:

1.LESS ACCURACY

2. LOW EFFICIENCY

PROPOSED SYSTEM :

Sentiment Classification: Algorithm 2 explains the sentiment classification which takes the corpus of subjective news sentences (SNS) as the input and outputs the sentiment of a sentence. It has performed by comparing each word in the sentence with the Sent WordNet positive keywords file (poskf) and negative keywords file (negkf). If the word is present in poskf, the sentiment of that sentence is considered as positive, and if the word is present in negkf, the sentiment of that sentence is considered as negative. Otherwise, the sentence is simply discarded as any word of that sentence is not matched with any of the keywords in negkf and poskf. In Algorithm 2, there is a high chance that some words in the sentence are matched with the negative keywords file, and some words in the same sentence are matched with positive keywords. In that scenario, it is hard to decide the sentiment of the sentence. To resolve this issue, we are keeping count variable to identify this kind of sentences. If the count is greater than one, the sentence is matched in both the lists poskf and negkf . So, we are adopting sentiment score to identify the actual sentiment of a sentence. To find the sentiment score of the sentence, calculate the number of positive words (PWS) and negative words (NWS) in the same sentence. Then, calculate the positive ratio and negative ratio

PROPOSED SYSTEM ADVANTAGES:

1.HIGH ACCURACY

2.HIGH EFFICIENCY

SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10

HARDWARE REQUIREMENTS:

 Processor : Core I3
 RAM Capacity : 2 GB
 Hard Disk : 250 GB
 Monitor : 15″ Color
 Mouse : 2 or 3 Button Mouse
 Key Board : Windows 08/10