Mining the real-time web: A novel approach to product recommendation

Abstract

Real-time web (RTW) services such as Twitter allow users to express their opinions and interests, often expressed in the form of short text messages providing abbreviated and highly personalized commentary in real-time. Although this RTW data is far from the structured data (movie ratings, product features, etc.) that is familiar to recommender systems research, it can contain useful consumer reviews on products, services and brands. This paper describes how Twitter-like short-form messages can be leveraged as a source of indexing and retrieval information for product recommendation. In particular, we describe how users and products can be represented from the terms used in their associated reviews. An evaluation performed on four di↵erent product datasets from the Blippr service shows the potential of this type of recommendation knowledge, and the experiments show that our proposed approach outperforms a more traditional collaborative-filtering based approach.

Sentiment analysis: A review and comparative analysis of web services

“…The previous subsections have shown the effectiveness of the different tools using standard collections; nonetheless, in other applications, tools for evaluating sentiments have been used to address real problems, for example, estimating votes in elections through Tweets (Tumasjan et al, 2010), recommending products according to customers' opinions (Garcia Esparza et al, 2012) or analyzing stock markets (Li et al, 2014;Smailović et al, 2014). Thus, following that idea, and with the aim of analyzing the usefulness of these tools to recommend products in a real scenario as many other works propose (Porcel et al, 2012;Tejeda-Lorente et al, 2014;Serrano-Guerrero et al, 2011, 2013, an experiment working with real comments collected from an important website is presented.…”

Mobility Network Evaluation in the User Perspective: Real-Time Sensing of Traffic Information in Twitter Messages

“…Liu offers a comprehensive introduction to the fields of Sentiment Analysis and Opinion Mining (Liu, 2012). Esparza et al (2012) investigate the way user-generated micro-blogging messages can be used as a new source for recommendation systems based on extracted opinions. Tsytsarau and Palpanas (2012) present a thorough review of the most popular algorithms for sentiment extraction in the literature and discuss their precision.…”

The Latest Research Progress of Personalized Information Recommend Based on the Tag

“…Although compared with the relational model expression this information is difficult to understand for recommendation system, RTW contains a large number of user preference information. They raised four data sets that can be used in RTW information collection [6] .…”