{"id":294,"date":"2018-04-27T08:23:08","date_gmt":"2018-04-27T07:23:08","guid":{"rendered":"http:\/\/generic.wordpress.soton.ac.uk\/aura\/?p=294"},"modified":"2018-05-03T22:32:21","modified_gmt":"2018-05-03T21:32:21","slug":"sentiment-analysis-tools-and-solutions","status":"publish","type":"post","link":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/2018\/04\/27\/aura-sentiment-analysis-tools-and-solutions\/","title":{"rendered":"Sentiment analysis tools and solutions"},"content":{"rendered":"

Opinion mining and sentiment analysis (OMSA)<\/strong> is a technically challenging problem that involves complex Artificial Intelligence (AI)<\/strong> and machine learning<\/strong> and has emerged over the last 15 years. Tools have been around for long to measure various parameters in areas such as the success of a marketing campaign, user engagement, audience targeting and segmentation, etc. <\/span><\/p>\n

The field has been a core element for B2C (Business to Customers)<\/strong> organisations. The leaders in sentiment analysis are Aura\u2019s competitors: Facebook, Twitter and YouTube. Many areas such as <\/span>stock markets, elections, disasters and medicine have extended the utilisation of sentiment analysis.<\/span><\/p>\n

With advancements in other computer science areas such as AI and machine learning, the evolution of sentiment analysis has been fast-paced. According\u00a0to data from Google Trends<\/strong>, there are nearly 9,000 papers published regarding sentiment analysis, and 99% of them have been posted in 2004 [1]<\/span><\/span><\/p>\n

\"\"
Figure 1 – Search activity relating to \u2018sentiment analysis\u2019, a screenshot of Google Trends results<\/figcaption><\/figure>\n

Most of the tools work with textual<\/strong>, and contextual<\/strong> sources. Lately, platforms have been developed to work with <\/span>non-textual<\/strong>, sentiment-bearing<\/strong> sources such as speech<\/span>. <\/span>IBM Watson<\/a> and Google Cloud Natual Language<\/a> have public APIs for sentiment analysis [2]<\/span>. These tools return a scorecard on various sentiments. <\/span><\/p>\n

Another platform, Qemotion <\/a>takes a different approach to the scorecard, it returns an emotion in terms of temperature. It claims to calculate emotional responses with 85% accuracy. These platforms are also capable of topic clustering<\/strong>, which can be used to realise the context of the text.\u00a0(Sifium, 2018)<\/span><\/p>\n

Many of the aforementioned platforms can be used to build Aura upon. They are very advanced with a very good accuracy. Given the learning nature of the algorithms, it would be better to a use an existing solution given its wide base of knowledge.<\/span><\/p>\n

References<\/strong><\/p>\n

[1] Arxiv.org. (2018). [online] Available at: https:\/\/arxiv.org\/pdf\/1612.01556.pdf <\/a>[Accessed 8 Apr. 2018].<\/p>\n

[2] Hootsuite Social Media Management. (2018). The Best Sentiment Analysis Tools for Social Media Marketers<\/i>. [online] Available at: https:\/\/blog.hootsuite.com\/social-media-sentiment-analysis-tools\/ [Accessed 8 Apr. 2018].<\/p>\n

Medium. (2018). Top Five Emotion \/ Sentiment Analysis APIs for understanding user sentiment trends.<\/i>. [online] Available at: https:\/\/medium.com\/@sifium\/top-five-emotional-sentiment-analysis-apis-116cd8d42055 [Accessed 8 Apr. 2018].<\/p>\n","protected":false},"excerpt":{"rendered":"

Opinion mining and sentiment analysis (OMSA) is a technically challenging problem that involves complex Artificial Intelligence (AI) and machine learning and has emerged over the last 15 years. Tools have been around for long to measure various parameters in areas such as the success of a marketing campaign, user engagement, …<\/p>\n","protected":false},"author":2986,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[38],"tags":[6,52,72,73,71],"class_list":["post-294","post","type-post","status-publish","format-standard","hentry","category-tools-analysis","tag-aura","tag-research","tag-sentiment-analysis-tools","tag-solutions","tag-tools-analysis"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/posts\/294","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/users\/2986"}],"replies":[{"embeddable":true,"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/comments?post=294"}],"version-history":[{"count":8,"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/posts\/294\/revisions"}],"predecessor-version":[{"id":690,"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/posts\/294\/revisions\/690"}],"wp:attachment":[{"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/media?parent=294"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/categories?post=294"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/generic.wordpress.soton.ac.uk\/aura\/wp-json\/wp\/v2\/tags?post=294"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}