Technology Trends

In this article, eWEEK reports about new smart carts announced by Fujitsu. After entering your shopping list on your Bluetooth-enabled PDA, you’ll go to your supermarket and pick a smart cart which will download your list on the rugged screen (read brat-proof) of its $1,200 unit. The system will lead you around the store, alert you about promotions, show you new recipes and update the shopping list in real time. It also can send messages to the deli or pharmacy sections and tell you when your order is ready. The U-Scan Shopper system allows you to remain anonymous and to receive only regular store promotions. Or you can use a loyalty card, receive targeted ads or recipes based on your shopping history, which will be maintained in the retailer’s databases. The article doesn’t say anything about shoppers who still use paper lists, but I bet these carts are still not smart enough to guess what is written on them. Read more…

Here is the rosy scenario imagined by eWEEK.

With a craving for broiled salmon, Jane quickly sifted through her spice cabinet only to find that her bottle of dill weed was nearly empty.

With a few clicks on her Bluetooth-enabled PDA, she updated her Web shopping list with the dill, and a window opened onscreen suggesting a new salmon recipe. It looked good, so she approved the recipe and her shopping list was instantly updated with all of the necessary items, omitting those that her kitchen already had in stock.

Jane drove the half-mile to her local supermarket where she grabbed a smart cart, scanned her loyalty card and saw her updated shopping list appear in front of her. It had been categorized by aisle, and the cart directed Jane to each item. While she was checking for brown spots on broccoli heads in the produce aisle, her cart signaled the pharmacy to prepare a prescription refill and sent an order for lunch meats to the deli.

Here is an example of what you’ll see on this smart cart’s screen. (Credit: Fujitsu Transaction Solutions Inc.) Here is a link to a larger version which is customizable by retailers to fit their own needs.

Now, let’s look at the Fujitsu’s business model for these smart carts.

Equipping an ordinary shopping cart with Fujitsu’s new U-Scan Shopper unit will cost about $1,200. That price also includes about 60 infrared triggers to be strategically placed along various store shelves to help the cart find its path around the store. Fujitsu is hoping to sell 100 carts at each typical grocery store, according to Vernon Slack, Fujitsu’s director of mobile solutions.

And now, here are more details about the essential part of the system, its screen.

Slack points to more practical advantages of Fujitsu’s design, such as their claim that their cart-handle-mounted unit (it’s literally bolted on) is small enough to allow for a child to sit in the traditional front-compartment, while some rival units are too large.

The “just less than two-pound” unit with the 6.5-inch display is surrounded with a quarter-inch of hardened Mylar plastic making it almost indestructible, even by a curious child, Slack said. The units are also sealed with a polycarbonate cover.

Slack sees the fact that the cart would already have the unit bolted to its bar when the customer arrives as an advantage over smart-cart approaches where the customer has to pick up a pad at customer service or at the entrance and place it in the cart.

The article from eWEEK also looks at the privacy concerns which could be raised by such devices. It also addresses the checkout issues — yes, you’ll still have to pay — and the delivery of personal ads.

Now, I have two questions for you. Would you like to find these smart carts at your local supermarket? And who will profit the most from these systems, the retailers or you?

Sources: Evan Schuman, eWEEK, February 16, 2005; Fujitsu Transaction Solutions Inc.

Related stories can be found in the following categories.

• Business Intelligence
  


• Human Computer Interface
  


• Pervasive Computing
  


• Wireless
  

Imagine you work for a company which introduces a new product. Obviously, you would want to know if the public likes it or not. But how would you find it? You could search the Web and read every possible document that mentions your product. This might be very time-consuming. Help is on the way, with a software that will scan the Web for you and separate the positive and negative reviews. This software might be based on research done at Cornell University and described by Technology Research News in “Software sorts out subjectivity.” The researchers are improving ’sentiment classification’ by removing neutral sentences. Their machine-learning method then applies only to subjective portions of the document. But the following negative statement, which contains only positive words, shows the difficulty to classify a sentence as positive or negative: “If you think this laptop is a great deal, I’ve got a nice bridge you might be interested in.” It may take a decade before such a system is widely available. Read more…

Here is how Technology Research News introduces the problem of automatic sentiment classification.

One of the fundamental challenges in getting computers to sort and analyze text is finding ways to automatically classify information.

Applications like search engines that group similar documents do so using topic-based categories. Sentiment analysis techniques add another dimension by determining the author’s attitude about a topic rather than just identifying a topic.

Existing techniques tend to concentrate on finding words, phrases and patterns that indicate sentiment. This has proven difficult, however. “This laptop is a great deal”, for instance, shows strong sentiment, but contains the same words as the neutral sentence “The release of this new laptop drew a great deal of media attention.”

So how do you teach a computer to ‘understand’ the meaning of words?

Researchers from Cornell University have devised a way to improve sentiment classification that sidesteps having to deal with meaning by instead concentrating on context. Their method weeds out neutral sentences. “Getting rid of neutral sentences like ‘The release of this new laptop drew a great deal of media attention’ [makes] the overall sentiment more obvious,” said Lillian Lee, an associate professor of computer science at Cornell University.

Here are more details about the method.

The researchers represented text as a network, or graph. “Imagine that each sentence is represented by a network point, or node,” said Lee. To model contextual information between each pair of sentence nodes, the researchers added a link whose strength represented how much the two sentences deserved the same label — objective or subjective — based on criteria including how close the sentences are to the text, and whether they are separated by a paragraph boundary.

The model also took into consideration the evidence within a sentence that the sentence is subjective or objective. Possible evidence that a sentence is subjective, for example, includes the presence of a word like ‘wonderful’, or ‘terrible’, said Lee.

Each sentence was linked strongly or weakly to a special subjective and objective nodes depending on the amount of evidence there was within the sentence that it was subjective or objective.

The sentences are then clustered into subjective and objective camps based on the strength of the links. This is a graph partitioning problem known as finding the minimum cut, and it can be solved exactly by a quick, efficient algorithm, said Lee.

And is this approach successful?

The method improved sentiment classification performance from 82.8 to 86.4 percent, which is statistically very significant, according to Lee. The method could eventually be used to maintain review-aggregator Web sites, to filter search results by viewpoint, and to track attitudes toward a given topic, she said.

When will be able to use such a software? And what will it be useful for?

It will take at least a decade before the system can readily handle unrestricted texts containing arbitrary rhetorical devices, she said.

The method could be used by search engines to sort or filter results by viewpoint to, for instance, help users distinguish between objective and biased Web sites, said Lee.

It could also be used to track changes in attitudes toward a given topic by, for instance, analyzing press articles, she said.

And companies could use the system to gather business intelligence such as finding out what people think of their products or the products of their competitors. “A computer company might crawl blogs to find out whether or not people like its latest laptop model,” said Lee.

The research work has been published in the Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, held July 21 to 26, 2004 in Barcelona, Spain under the title “A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts.”

Here are two links to the abstract and to the full paper (PDF format, 8 pages, 264 KB). The above diagram was extracted from this paper.

Sources: Kimberly Patch, Technology Research News, November 17/24, 2004; Cornell University website

Related stories can be found in the following categories.

• Artificial Intelligence
  


• Business Intelligence
  


• Search
  


• Software