Understanding what concerns consumers: a semantic approach to product feature extraction from consumer reviews

Abstract

The Web has become an excellent source for gathering consumer opinions (more specifically, consumer reviews) about products. Consumer reviews are essential for retailers and product manufacturers to understand the general responses of customers to their products and improve their marketing campaigns or products accordingly. In addition, consumer reviews enable retailers to recognize the specific preferences of each customer, which facilitates effective marketing decisions. As the number of consumer reviews expands, it is essential and desirable to develop an efficient and effective sentiment analysis technique that is capable of extracting product features stated in consumer reviews (i.e., product feature extraction) and determining the sentiments (positive or negative semantic orientations) of consumers for these product features (i.e., opinion orientation identification). Product feature extraction is critical to sentiment analysis, because its effectiveness significantly affects the performance of opinion orientation identification, as well as the ultimate effectiveness of sentiment analysis. Therefore, this study concentrates on product feature extraction from consumer reviews.

An Extended HITS Algorithm on Bipartite Network for Features Extraction of Online Customer Reviews

“…People often use nouns to denote product features and use adjectives to express their sentiments toward specific product features [44]. In the context of feature extraction, a noun or noun phrase is more likely to be a feature if it is modified by quite a few adjectives [17].…”

Sentiment Mining from Text: A Technical Review

“…Several applications of sentiment mining require classification of the expressed opinions as positive, negative or neutral [4], [26], [27], [28], [29], [30]. Automatic classification of the 'sentiment polarity' or 'orientation' of text is a challenging task.…”

“…Recent approaches for sentiment polarity classification are based on semantic feature set extraction [4], [28], [29]. Feature based methods for polarity classification require mining of a meaningful feature set from the opinion bearing text before tagging the sentiment polarity, which is a challenging task.…”

“…For instance, websites that post reviews of electronic products such as smartphones would frequently refer to noun features such as 'touchscreen', 'camera' etc. In order to identify nouns features and their associated adjective/adverb descriptors from text, pre-processing steps like sentence boundary detection and parts-of-speech (POS) tagging [4], [28], [34], [35] are performed. Moreover, since all nouns cannot be considered as semantic features a refining/reducing step is required.…”

“…Moreover, since all nouns cannot be considered as semantic features a refining/reducing step is required. The various methods in literature to extract useful features comprise Apriori approach [4], [28], [31], Seed-set expansion approach [29], [34] and Multiword based approach [35], [36]. These three approaches are briefly discussed next.…”