Conversational Collaborative Recommendation – An Experimental Analysis

Rafter, Rachael; Smyth, Barry

doi:10.1007/s10462-005-9004-8

Cited by 20 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Rafter and Smyth [22] a conversational collaborative system is presented where recommendations are handed over to the user through a natural language interface. The authors show how the feedback obtained from the interaction with the users can help to differentiate between the user's long-term stored preferences, and current short-term requirements.…”

Section: Discussionmentioning

confidence: 99%

Evaluating the impact of different virtual characters in product recommendations

Reategui

Fruet

Filho

2006

Proceedings of VII Brazilian Symposium on Human Factors in Computing Systems

View full text Add to dashboard Cite

This paper presents an evaluation of the effect that distinct interface characters could have on the users' perception of their interaction with an ecommerce website. A recommender system has been integrated to the characters' architecture, with the goal of assessing their impact in making personalized recommendations. The characters used to interact with the users had different features such as being a known or an unknown person; being represented by an anthropomorphic figure or not. In spite of these differences, the characters also had a lot of similarities: they used the same language and had the same strategy for recommending products. They also had the same type of graphical representation. An experiment involving 180 students was set up, in which students had to complete a few purchases in an ecommerce website where the virtual characters gave tips and suggested products related to the users' perceived interests. The results of the experiment are presented here, as well as conclusions and direction for future work.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluating the impact of different virtual characters in product recommendations

Reategui

Fruet

Filho

2006

Proceedings of VII Brazilian Symposium on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…More advanced recommender systems have incorporated explicit user feedback in the recommendation process to produce more effective recommendations [Chen and Pu 2007]. More recently, researchers have developed conversational recommender systems that can adaptively learn interaction strategies to better assist users in achieving their goals [Rafter and Smyth 2005;Mahmood and Ricci 2007;Viappiani et al 2007]. Compared to the existing work, Pharos employs a hybrid interaction strategy.…”

Section: Related Workmentioning

confidence: 99%

Who is Doing What and When

Zhao

Zhou

Zhang

et al. 2011

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

Content-centric social Web sites, such as discussion forums and blog sites, have flourished during the past several years. These sites often contain overwhelming amounts of information that are also being updated rapidly. To help users locate their interests at such sites (e.g., interesting blogs to read or discussion forums to join), researchers have developed a number of recommendation technologies. However, it is difficult to make effective recommendations for new users (a.k.a. the cold start problem) due to a lack of user information (e.g., preferences and interests). Furthermore, the complexity of recommendation algorithms often prevents users from comprehending let alone trusting the recommended results. To tackle these above two challenges, we are building a social map-based recommender system called Pharos. A social map summarizes users' content-related social behavior over time (e.g., reading, writing, and commenting behavior during the past week) as a set of latent communities. For a given time interval, each community is characterized by the theme of the content being discussed and the key people involved. By discovering, ranking, and displaying the most popular latent communities at different time intervals, Pharos creates a time-sensitive, visual social map of a Web site. This enables new users to obtain a quick overview of the site, alleviating the cold start problem. Furthermore, we use the social map as a context to help explain Pharos-recommended content and people. Users can also interactively explore the social map to locate the content in which they are interested or people that are not being explicitly recommended, compensating for the imperfections in the recommendation algorithms. We have developed several Pharos applications, one of which is deployed within our company. Our preliminary evaluation of the deployed application shows the usefulness of Pharos.

show abstract

“…A review of these techniques is also given by Adomavicius and Tuzhilin in [2], where Decision Trees, Clustering, Artificial Neural Networks and Bayesian classifiers are mentioned. Our system also takes into consideration the current user's interest context [23], which is similar to the idea of using short and long term profiles explained in [17].…”

Section: Related Workmentioning

confidence: 99%

Discerning Relevant Model Features in a Content-based Collaborative Recommender System

Bellogín

Cantador

Castells

et al. 2010

Preference Learning

View full text Add to dashboard Cite

Abstract. Recommender systems suggest users information items they may be interested in. User profiles or usage data are compared with some reference characteristics, which may belong to the items (content-based approach), or to other users in the same context (collaborative filtering approach). These items are usually presented as a ranking, where the more relevant an item is predicted to be for a user, the higher it appears in the ranking. In this scenario, a preferential order has to be inferred, and therefore, preference learning methods can be naturally helpful. The relevant recommendation model features for the learningbased enhancements explored in this work comprise parameters of the recommendation algorithms, and user-related attributes. In the researched approach, machine learning techniques are used to discover which model features are relevant in providing accurate recommendations. The assessment of relevant model features, which is the focus of this paper, is envisioned as the first step in a learning cycle in which improved recommendation models are produced and executed after the discovery step, based on the findings that result from it.

show abstract

Conversational Collaborative Recommendation – An Experimental Analysis

Cited by 20 publications

References 6 publications

Evaluating the impact of different virtual characters in product recommendations

Evaluating the impact of different virtual characters in product recommendations

Who is Doing What and When

Discerning Relevant Model Features in a Content-based Collaborative Recommender System

Contact Info

Product

Resources

About