Sentiment analysis, or opinion mining, is a natural language processing technique used to determine whether data is positive, negative or neutral. Sentiment analysis is often performed on textual data to help businesses monitor brand and product sentiment in customer feedback, and understand customer needs. The main problems that exist in the sentiment analysis technique are: inability to perform well in different domains, adequate accuracy and performance in sentiment analysis based on insufficient labeled data, incapability to deal with complex sentences that require more than sentiment words and simple analyzing.
Besides the use of marketing tools, trust, is also a vital factor that needs to be delivered on an e-commerce website (Kau et al. 2003), so much so that research has identified this as another step in the online buying decision process (Constantinides 2004). Figure X represents this online buying process.
Figure 1: Factors Affecting the Online Consumer’s Behaviour (Constantinides, 2004)
2.2.2 Online Shopping Motivation (38/200 words)
There may be various reasons why consumers would prefer to shop online rather than in brick-and-mortar stores, including time flexibility and the opportunity to engage in impulsive buying or directly responding to an advertisement (Kau et al. 2003).
2.1.3 Age and Gender Attitude towards Online Shopping
Males have been described as the first profile of a typical internet shopper (Sorce et al. 2005), but this has now changed. Studies show that there are no preferential differences between genders when shopping online (Settle & Alreck 2002).
When it comes to age differences, Sorce (2005) suggests that younger consumers agree that online shopping is more convenient, even if, as a group, they are more engaged in the search for different products rather than actually purchasing the product. The study continues by showing that, older consumers, on the other hand, tend to purchase more in relation to the amount of search they conduct for the different products.
