SiteAdvisor - a site review plugin
SiteAdvisor - a site review plugin to simplify the search process
Searching for help in the web is akin to finding a needle in a haystack. We need to streamline the search process, helping users find relevant search results fast. Introducing SiteAdvisor, a plugin that improves search experience in search engines via human reviews of links.
Team membersKatherine Fennedy, Marie Therese Siew Hui Lin, Ignasia Hanny, Javier Pey Jia Jie, Er Ding Xuan, Thileepan Stalin
Our group proposes to design a plugin which improves the search experience in search engines by providing crowdsourced human reviews of links. After viewing a page, users can rate the article and give comments based on how the page has helped them. The algorithm will filter the comments and provide the 3 most suitable keywords for that page (eg. useful, beginner level, step by step), along with the ratings. Keywords comment on the level of difficulty (beginner, expert, etc) , subject, ease of reading. Future users will be able to view the quality of the content provided and also if the content is relevant to the level that they require (eg beginner vs advanced). This helps to enhance the search process in light of the overwhelming amount of information on the web. It helps the user to solve their academic queries and also reduce their frustrations in their learning journey. We choose to use the medium of online reviews because reviews have been an effective tool in domains like e-commerce and book recommendations.
Success of the plugin can be measured via the number of downloads, ratings, user retention (do they still use it after half a year?).
Searching the query “Mathematics” gives about 594,000,000 results. There is a lot of information out there, but how do you decide which one is relevant to you? Searching the web for help to solve an academic problem can be like searching for a needle in a haystack at times. We may open many tabs but none of them would give us the proper information that is required in our studies.
Users, ranging from students to academic researchers, are frustrated, with comments such as “Information searching is time consuming.”, “I have encountered results not matching to what I searched.” or “The top result is not suitable”. In light of the overwhelming amount of information available on the web, there is an urgent need to streamline the search process, in order to help the user obtain relevant search results.
Solution target group
Learners which includes both students and academics. They will benefit because their searches would lead to relevant results and hence, help to significantly save time during the search process. As such, they would be able to assign their time into something more productive during their busy schedule.
It would help users streamline their search process in light of the overwhelming amount of information on the web. This will help the learning process to be less frustrating and more enjoyable. Users will be able to spend less time on the search process and spend more time on critical thinking for their academic problem.
We can measure impact via:
- Tracking the number of “helpful” articles that were recommended by our plugin.
- Calculating the percentage of the people who found the recommended article useful.
- Customer retention: whether users would still utilize the plugin after a few months of usage.
- Number of downloads.
- Ratings and reviews of our plugin.
Solution tweet textA web plugin that leverages user reviews to provide evaluation of websites in terms of their query relevancy and qualitative analysis of content.
Search engines utilize SEO (eg the page rank algorithm). Our solution complements and enhances the results of search engines by involving crowdsourcing which provides useful human feedback on whether the query is answered.
There are websites that filter research papers (Iris.ai) and business information (Bitvore) but these are domain specific, and involve a topical search. We want to develop a free (for now) plug-in that filters keywords to show the relevancy of sources with respect to the query, via a human touch (reviews and ratings of other users). Our plugin is not limited to specific domains, but can be utilized in many domains via the utilisation of different keywords.
The plugin is not just limited to an academic context but could also be implemented into other fields, namely tourism and e-commerce. The recommendation feature via the utilisation of different keywords is a model that can be interchanged easily between different domains.
A testing phase will be conducted before the official launch. We will engage the community in our university and invite users to use the plugin to allow us to investigate what types of keywords will help learners filter information faster. For eg, are elementary, beginner, advanced the appropriate words to differentiate the level of difficulty of an article? We want to ensure that our algorithms are able to test for the right keywords.
In the short term, we will work on partnership with other universities. Moreover, the collaboration with SUTD modules such as Design 3.007 can provide us with valuable feedback if the plugin is indeed more efficient in searching for relevant results.
In the long term, we will work towards being credible. The next step would then be to collaborate with for-profit education websites such as Khan Academy and Udemy. Our plugin can help them increase their SEO through keywords that our algorithm learnt. These keywords allow the companies to better target more specific groups of learners.
Solution team work
There was good communication between all the members and everyone gave extremely constructive insights to the problem. All members were able to relate to the pain points highlighted in this problem during their journey as a student. As such, there was always steady progress and improvements in ideas and discussions. The brainstorming of current systems in the market allowed us to open up avenues and opportunities were we could come in to implement novel and unique solutions in areas that have never been tackled before. All in all, this was an extremely fruitful experience for everyone and we would definitely continue to work as a team in the future.
* Climate-KIC publishes the proposed solutions developed during the DigiEduHack event solely for the purposes of facilitating public access to the information concerning ideas and shall not be liable regarding any intellectual property or other rights that might be claimed to pertain to the implementation or use any of the proposed solutions shared on its website neither does it represent that it has made any effort to identify any such rights. Climate-KIC cannot guarantee that the text of the proposed solution is an exact reproduction of the proposed solution. This database is general in character and where you want to use and develop a proposed solution further, this is permitted provided that you acknowledge the source and the team which worked on the solution by using the team’s name indicated on the website.