{"id":198,"date":"2019-04-25T21:52:51","date_gmt":"2019-04-26T01:52:51","guid":{"rendered":"http:\/\/community.mis.temple.edu\/ashlinbc\/?page_id=198"},"modified":"2019-04-25T21:52:51","modified_gmt":"2019-04-26T01:52:51","slug":"research","status":"publish","type":"page","link":"https:\/\/community.mis.temple.edu\/ashlinbc\/research\/","title":{"rendered":"RESEARCH"},"content":{"rendered":"

SENTIMENT ANALYSIS<\/strong><\/span><\/p>\n

Sentiment analysis is an analysis that extracts subjective information from the source material. This way of contextual mining is primarily used to classify the source material as positive, negative or neutral. Furthermore, it could be intent analysis, a contextual semantic search which are some applications of this idea (Gupta, 2019). The very application of sentimental analysis is to help large enterprises to perform market research, gain public opinion and learn customer purchase patterns and soon. Sentiment analysis APIs are often used by data analytics companies for the same purpose(“Sentiment Analysis | Lexalytics”, 2019). Though this type of analysis is useful for business in many ways, they have certain drawbacks. Sarcasm, humor, irony or any such kind of speech would be difficult to detect through this process. When false negative statements are posted by people in social media, it will be classified incorrectly (B Omondi Ochieng, Loki & Sambuli, 2016). Hence, human sentiments in online statements cannot be deciphered with this algorithm.<\/span><\/p>\n

An example of how sentiment analysis has been applied in practice: Expedia in Canada learned about the negative response for the music in one of their commercials through sentiment analysis. In their newer version of the commercial, they smashed the offending violin, in order to respond to that sentiment (Marr, n.d.).<\/span><\/p>\n

\"\"<\/span><\/p>\n

In the MIS 2502: Data Analytics class we have learned about structured, unstructured and semi-structured data. Sentiment analysis is performed mostly on unstructured data since social media posts, articles are all unstructured including texts and images. We can convert the unstructured data from Twitter or any platform to a semi-structured form such as CSV, XML or JSON and analyze the data to provide the outcome. In the MIS 0855: Data Science class, a small level sentiment analysis was performed as a part of the learning materials and a snapshot is provided above.<\/span><\/p>\n

WORKS CITED<\/strong><\/span><\/p>\n

B Omondi Ochieng, S., Loki, M., & Sambuli, N. (2016). LIMITATIONS OF SENTIMENT ANALYSIS ON FACEBOOK DATA. International Journal Of Social Sciences And Information Technology Journal Of Social Sciences And Information Technology<\/em>, 2<\/em>, 427.<\/span><\/p>\n

Gupta, S. (2019). Sentiment Analysis: Concept, Analysis and Applications<\/em>. [online] <\/span>Towards Data Science. Available at: https:\/\/towardsdatascience.com\/sentiment-analysis-concept-analysis-and-applications-6c94d6f58c17 [Accessed 23 Apr. 2019].<\/span><\/p>\n

Marr, B. What Is Sentiment <\/span>Analysis ?And What Are Its Real-World Applications. Retrieved from https:\/\/www.bernardmarr.com\/default.asp?contentID=1747<\/span><\/p>\n

Sentiment Analysis | Lexalytics. (2019). Retrieved from https:\/\/www.lexalytics.com\/technology\/sentiment-analysis<\/a><\/span><\/p>\n

 <\/p>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

SENTIMENT ANALYSIS Sentiment analysis is an analysis that extracts subjective information from the source material. This way of contextual mining is primarily used to classify the source material as positive, negative or neutral. Furthermore, it could be intent analysis, a contextual semantic search which are some applications of this idea (Gupta, 2019). The very application […]<\/p>\n","protected":false},"author":20407,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-198","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/community.mis.temple.edu\/ashlinbc\/wp-json\/wp\/v2\/pages\/198","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/community.mis.temple.edu\/ashlinbc\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/community.mis.temple.edu\/ashlinbc\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/community.mis.temple.edu\/ashlinbc\/wp-json\/wp\/v2\/users\/20407"}],"replies":[{"embeddable":true,"href":"https:\/\/community.mis.temple.edu\/ashlinbc\/wp-json\/wp\/v2\/comments?post=198"}],"version-history":[{"count":1,"href":"https:\/\/community.mis.temple.edu\/ashlinbc\/wp-json\/wp\/v2\/pages\/198\/revisions"}],"predecessor-version":[{"id":201,"href":"https:\/\/community.mis.temple.edu\/ashlinbc\/wp-json\/wp\/v2\/pages\/198\/revisions\/201"}],"wp:attachment":[{"href":"https:\/\/community.mis.temple.edu\/ashlinbc\/wp-json\/wp\/v2\/media?parent=198"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}